{"id":44507,"topic":"ai","source":"Harvard University","title":"Can AI Make Wearable Technologies and Assistive Devices More Helpful? - Harvard University","url":"https://seas.harvard.edu/news/can-ai-make-wearable-technologies-and-assistive-devices-more-helpful","url_hash":"52351d61446d5aaf39cf4d86e5d13d9a38da1370","author":"","summary":"Can AI Make Wearable Technologies and Assistive Devices More Helpful? Harvard University","content":"News\nPatrick Slade is an Assistant Professor of Bioengineering at the Harvard John A. Paulson School of Engineering and Applied Sciences (SEAS). His research combines wearable robotics, biomechanics, sensing, and artificial intelligence to help people move more easily and safely in everyday life. His lab develops technologies that can measure human movement, adapt assistance to individual users, and support people with mobility or navigation challenges. The following Q&A was developed from interviews with Slade. It has been edited for clarity, length, and context.\nQ: How does AI improve wearable technologies and assistive devices?\nA: One thing we have learned in wearable robotics is that putting a motor on someone does not necessarily make it easier for them to move. In some cases, it can actually make movement harder because the device is not working in harmony with the person.\nWe all move a little differently. People vary in their strength, balance, motor control, and movement patterns, and those differences become even more important in patient populations. A device that helps one person may not help another in the same way.\nAI gives us tools to better understand those differences. We can combine wearable sensors with machine-learning models to estimate things that are difficult to measure outside the lab, such as energy expenditure, walking speed, movement asymmetry, or joint loading. We can then use that information to personalize the assistance — adjusting when it is delivered, how much is provided, and what outcome we are trying to improve.\nQ: What are the limitations of current wearables, like smartwatches?\nA: Consumer wearables are very good at collecting data, but some of the metrics they report can be surprisingly inaccurate. Estimates of energy expenditure, or calories burned, can sometimes have errors on the order of 40 to 80 percent.\nPart of the problem is that many devices rely on indirect signals such as heart rate or wrist motion. Those signals can be useful, but they do not always reflect the mechanical work the body is doing. When you walk or run, much of the energy expenditure comes from the muscles in your legs, not from the movement of your wrist.\nOur approach is to use signals that are more closely connected to biomechanics. For example, a smartphone carried in a pocket can measure acceleration. We can combine that information with machine-learning models and established principles from physics to estimate meaningful measures such as energy expenditure more accurately.\nThe goal is not simply to collect more data. It is to identify the signals that matter most and use AI in a way that reflects how the body actually works.\nQ: What is the biggest challenge in developing wearable and assistive technologies?\nA: Personalization is one of the central challenges in our research. People vary in their movement patterns, strength, balance, motor control, anatomy, and goals. Those differences become especially important for people who have experienced a stroke, people with knee osteoarthritis or knee pain, older adults, and people with blindness or visual impairment.\nA fixed controller might help one person and hinder another. Instead, we want the technology to learn how a particular person moves and determine what kind of support is most useful.\nFor a wearable robot, that might mean adjusting when assistance is delivered, how much force is applied, or which outcome the system is trying to improve. We might tune the device to reduce energy expenditure, increase walking speed, improve symmetry between the legs, or reduce loading on a painful knee.\nWe also need these systems to adapt outside controlled laboratory settings. People walk at different speeds, change direction, climb stairs, encounter uneven ground, and perform activities that may not appear in a training dataset. Our existing knowledge of human movement can help make the technology more robust and trustworthy.\nQ: Can you give examples of AI-powered assistive technologies in practice?\nA: One example is our work with people who have experienced a stroke. We can use wearable sensors and AI to estimate walking speed and asymmetry between the paretic and non-paretic legs. That information can help us personalize a wearable robot and determine how the device should assist the person.\nAnother application involves people with knee osteoarthritis or knee pain. In that work, we estimate the load passing through the knee and explore how an assistive device might reduce it.\nWe are also developing navigation technology for people with blindness or visual impairment. The system uses a smartphone camera, GPS, and motion data to identify features such as sidewalks, curb cuts, crosswalks, and obstacles. It then provides audio feedback through open-ear headphones to help guide the user.\nAcross these projects, AI allows the technology to interpret complex information and adapt assistance to the person and the environment.\nQ: What is the future of AI-powered wearable and assistive technologies?\nA. I think it is realistic that, within the next several years, people will be able to buy wearable devices that personalize themselves automatically using AI. These systems could support older adults, people with mobility impairments, workers performing physically demanding tasks, or anyone who wants help remaining active.\nAn e-bike is a useful analogy. It does not replace cycling; it provides enough assistance to make cycling more accessible. Wearable robotics could play a similar role by making movement easier, reducing pain or fatigue, and helping people continue doing the activities that matter to them.\nTopics: AI / Machine Learning, Bioengineering, Robotics, Wearable Devices\nCutting-edge science delivered direct to your inbox.\nJoin the Harvard SEAS mailing list.","image_url":"https://seas.harvard.edu/sites/default/files/styles/opengraph/public/2026-07/2024%20Patrick%20Slade-44.jpg?h=24375d97&itok=6uyNzXnU","lang":"en","published_at":"2026-07-23T13:12:14+00:00","fetched_at":"2026-07-23T14:15:03+00:00","status":"read","starred":0,"extract_state":"ok","summary_auto":"News\nPatrick Slade is an Assistant Professor of Bioengineering at the Harvard John A. His research combines wearable robotics, biomechanics, sensing, and artificial intelligence to help people move more easily and safely in everyday life.","cluster_id":null,"extract_retries":0,"extract_error":null,"contract_version":"news_item.v1","format_contract_version":"news_item_formats.v1","dedup_url":"https://seas.harvard.edu/news/can-ai-make-wearable-technologies-and-assistive-devices-more-helpful","quality_profile":{"profile_version":"extraction_quality.v2","bucket":"high","confidence":0.9,"failure_kind":"none","retryable":false,"retry_after_attempts":0,"reason":"High confidence: full text extraction produced 5819 characters.","operator_guidance":{"severity":"ok","recommended_action":"trust_full_text","next_step":"Use the extracted full text as the primary article source.","operator_label":"Ready","can_retry":false,"can_use_summary":false,"diagnostics_required":false},"content_depth":{"contract_version":"content_depth.v1","category":"full_text","label":"Full text","has_full_text":true,"has_summary":true,"content_length":5819,"summary_length":238,"usable_text_length":5819,"source_field":"content"},"legacy_collapsed":false,"signals":{"extract_state":"ok","extract_error":null,"extract_retries":0,"content_length":5819,"summary_length":238}},"news_item":{"id":44507,"canonical_url":"https://seas.harvard.edu/news/can-ai-make-wearable-technologies-and-assistive-devices-more-helpful","source_url":"https://seas.harvard.edu/news/can-ai-make-wearable-technologies-and-assistive-devices-more-helpful","title":"Can AI Make Wearable Technologies and Assistive Devices More Helpful? - Harvard University","source_name":"Harvard University","author":null,"published_at":"2026-07-23T13:12:14+00:00","locale":"en","topic":"ai","tags":[],"rss_summary":"Can AI Make Wearable Technologies and Assistive Devices More Helpful? Harvard University","full_text":"News\nPatrick Slade is an Assistant Professor of Bioengineering at the Harvard John A. Paulson School of Engineering and Applied Sciences (SEAS). His research combines wearable robotics, biomechanics, sensing, and artificial intelligence to help people move more easily and safely in everyday life. His lab develops technologies that can measure human movement, adapt assistance to individual users, and support people with mobility or navigation challenges. The following Q&A was developed from interviews with Slade. It has been edited for clarity, length, and context.\nQ: How does AI improve wearable technologies and assistive devices?\nA: One thing we have learned in wearable robotics is that putting a motor on someone does not necessarily make it easier for them to move. In some cases, it can actually make movement harder because the device is not working in harmony with the person.\nWe all move a little differently. People vary in their strength, balance, motor control, and movement patterns, and those differences become even more important in patient populations. A device that helps one person may not help another in the same way.\nAI gives us tools to better understand those differences. We can combine wearable sensors with machine-learning models to estimate things that are difficult to measure outside the lab, such as energy expenditure, walking speed, movement asymmetry, or joint loading. We can then use that information to personalize the assistance — adjusting when it is delivered, how much is provided, and what outcome we are trying to improve.\nQ: What are the limitations of current wearables, like smartwatches?\nA: Consumer wearables are very good at collecting data, but some of the metrics they report can be surprisingly inaccurate. Estimates of energy expenditure, or calories burned, can sometimes have errors on the order of 40 to 80 percent.\nPart of the problem is that many devices rely on indirect signals such as heart rate or wrist motion. Those signals can be useful, but they do not always reflect the mechanical work the body is doing. When you walk or run, much of the energy expenditure comes from the muscles in your legs, not from the movement of your wrist.\nOur approach is to use signals that are more closely connected to biomechanics. For example, a smartphone carried in a pocket can measure acceleration. We can combine that information with machine-learning models and established principles from physics to estimate meaningful measures such as energy expenditure more accurately.\nThe goal is not simply to collect more data. It is to identify the signals that matter most and use AI in a way that reflects how the body actually works.\nQ: What is the biggest challenge in developing wearable and assistive technologies?\nA: Personalization is one of the central challenges in our research. People vary in their movement patterns, strength, balance, motor control, anatomy, and goals. Those differences become especially important for people who have experienced a stroke, people with knee osteoarthritis or knee pain, older adults, and people with blindness or visual impairment.\nA fixed controller might help one person and hinder another. Instead, we want the technology to learn how a particular person moves and determine what kind of support is most useful.\nFor a wearable robot, that might mean adjusting when assistance is delivered, how much force is applied, or which outcome the system is trying to improve. We might tune the device to reduce energy expenditure, increase walking speed, improve symmetry between the legs, or reduce loading on a painful knee.\nWe also need these systems to adapt outside controlled laboratory settings. People walk at different speeds, change direction, climb stairs, encounter uneven ground, and perform activities that may not appear in a training dataset. Our existing knowledge of human movement can help make the technology more robust and trustworthy.\nQ: Can you give examples of AI-powered assistive technologies in practice?\nA: One example is our work with people who have experienced a stroke. We can use wearable sensors and AI to estimate walking speed and asymmetry between the paretic and non-paretic legs. That information can help us personalize a wearable robot and determine how the device should assist the person.\nAnother application involves people with knee osteoarthritis or knee pain. In that work, we estimate the load passing through the knee and explore how an assistive device might reduce it.\nWe are also developing navigation technology for people with blindness or visual impairment. The system uses a smartphone camera, GPS, and motion data to identify features such as sidewalks, curb cuts, crosswalks, and obstacles. It then provides audio feedback through open-ear headphones to help guide the user.\nAcross these projects, AI allows the technology to interpret complex information and adapt assistance to the person and the environment.\nQ: What is the future of AI-powered wearable and assistive technologies?\nA. I think it is realistic that, within the next several years, people will be able to buy wearable devices that personalize themselves automatically using AI. These systems could support older adults, people with mobility impairments, workers performing physically demanding tasks, or anyone who wants help remaining active.\nAn e-bike is a useful analogy. It does not replace cycling; it provides enough assistance to make cycling more accessible. Wearable robotics could play a similar role by making movement easier, reducing pain or fatigue, and helping people continue doing the activities that matter to them.\nTopics: AI / Machine Learning, Bioengineering, Robotics, Wearable Devices\nCutting-edge science delivered direct to your inbox.\nJoin the Harvard SEAS mailing list.","excerpt":"News\nPatrick Slade is an Assistant Professor of Bioengineering at the Harvard John A. His research combines wearable robotics, biomechanics, sensing, and artificial intelligence to help people move more easily and safely in everyday life.","extraction":{"state":"ok","confidence":0.9,"error":null,"explanation":"High confidence: full text extraction produced 5819 characters.","diagnostics_url":"/api/diagnose?url=https%3A//seas.harvard.edu/news/can-ai-make-wearable-technologies-and-assistive-devices-more-helpful","quality_profile":{"profile_version":"extraction_quality.v2","bucket":"high","confidence":0.9,"failure_kind":"none","retryable":false,"retry_after_attempts":0,"reason":"High confidence: full text extraction produced 5819 characters.","operator_guidance":{"severity":"ok","recommended_action":"trust_full_text","next_step":"Use the extracted full text as the primary article source.","operator_label":"Ready","can_retry":false,"can_use_summary":false,"diagnostics_required":false},"content_depth":{"contract_version":"content_depth.v1","category":"full_text","label":"Full text","has_full_text":true,"has_summary":true,"content_length":5819,"summary_length":238,"usable_text_length":5819,"source_field":"content"},"legacy_collapsed":false,"signals":{"extract_state":"ok","extract_error":null,"extract_retries":0,"content_length":5819,"summary_length":238}}},"display_formats":["compact","card","full","digest_section","json"]},"daily_stack_record":{"title":"Can AI Make Wearable Technologies and Assistive Devices More Helpful? - Harvard University","url":"https://seas.harvard.edu/news/can-ai-make-wearable-technologies-and-assistive-devices-more-helpful","summary":"News\nPatrick Slade is an Assistant Professor of Bioengineering at the Harvard John A. His research combines wearable robotics, biomechanics, sensing, and artificial intelligence to help people move more easily and safely in everyday life.","source":"Harvard University","date":"2026-07-23T13:12:14+00:00","content":"News\nPatrick Slade is an Assistant Professor of Bioengineering at the Harvard John A. Paulson School of Engineering and Applied Sciences (SEAS). His research combines wearable robotics, biomechanics, sensing, and artificial intelligence to help people move more easily and safely in everyday life. His lab develops technologies that can measure human movement, adapt assistance to individual users, and support people with mobility or navigation challenges. The following Q&A was developed from interviews with Slade. It has been edited for clarity, length, and context.\nQ: How does AI improve wearable technologies and assistive devices?\nA: One thing we have learned in wearable robotics is that putting a motor on someone does not necessarily make it easier for them to move. In some cases, it can actually make movement harder because the device is not working in harmony with the person.\nWe all move a little differently. People vary in their strength, balance, motor control, and movement patterns, and those differences become even more important in patient populations. A device that helps one person may not help another in the same way.\nAI gives us tools to better understand those differences. We can combine wearable sensors with machine-learning models to estimate things that are difficult to measure outside the lab, such as energy expenditure, walking speed, movement asymmetry, or joint loading. We can then use that information to personalize the assistance — adjusting when it is delivered, how much is provided, and what outcome we are trying to improve.\nQ: What are the limitations of current wearables, like smartwatches?\nA: Consumer wearables are very good at collecting data, but some of the metrics they report can be surprisingly inaccurate. Estimates of energy expenditure, or calories burned, can sometimes have errors on the order of 40 to 80 percent.\nPart of the problem is that many devices rely on indirect signals such as heart rate or wrist motion. Those signals can be useful, but they do not always reflect the mechanical work the body is doing. When you walk or run, much of the energy expenditure comes from the muscles in your legs, not from the movement of your wrist.\nOur approach is to use signals that are more closely connected to biomechanics. For example, a smartphone carried in a pocket can measure acceleration. We can combine that information with machine-learning models and established principles from physics to estimate meaningful measures such as energy expenditure more accurately.\nThe goal is not simply to collect more data. It is to identify the signals that matter most and use AI in a way that reflects how the body actually works.\nQ: What is the biggest challenge in developing wearable and assistive technologies?\nA: Personalization is one of the central challenges in our research. People vary in their movement patterns, strength, balance, motor control, anatomy, and goals. Those differences become especially important for people who have experienced a stroke, people with knee osteoarthritis or knee pain, older adults, and people with blindness or visual impairment.\nA fixed controller might help one person and hinder another. Instead, we want the technology to learn how a particular person moves and determine what kind of support is most useful.\nFor a wearable robot, that might mean adjusting when assistance is delivered, how much force is applied, or which outcome the system is trying to improve. We might tune the device to reduce energy expenditure, increase walking speed, improve symmetry between the legs, or reduce loading on a painful knee.\nWe also need these systems to adapt outside controlled laboratory settings. People walk at different speeds, change direction, climb stairs, encounter uneven ground, and perform activities that may not appear in a training dataset. Our existing knowledge of human movement can help make the technology more robust and trustworthy.\nQ: Can you give examples of AI-powered assistive technologies in practice?\nA: One example is our work with people who have experienced a stroke. We can use wearable sensors and AI to estimate walking speed and asymmetry between the paretic and non-paretic legs. That information can help us personalize a wearable robot and determine how the device should assist the person.\nAnother application involves people with knee osteoarthritis or knee pain. In that work, we estimate the load passing through the knee and explore how an assistive device might reduce it.\nWe are also developing navigation technology for people with blindness or visual impairment. The system uses a smartphone camera, GPS, and motion data to identify features such as sidewalks, curb cuts, crosswalks, and obstacles. It then provides audio feedback through open-ear headphones to help guide the user.\nAcross these projects, AI allows the technology to interpret complex information and adapt assistance to the person and the environment.\nQ: What is the future of AI-powered wearable and assistive technologies?\nA. I think it is realistic that, within the next several years, people will be able to buy wearable devices that personalize themselves automatically using AI. These systems could support older adults, people with mobility impairments, workers performing physically demanding tasks, or anyone who wants help remaining active.\nAn e-bike is a useful analogy. It does not replace cycling; it provides enough assistance to make cycling more accessible. Wearable robotics could play a similar role by making movement easier, reducing pain or fatigue, and helping people continue doing the activities that matter to them.\nTopics: AI / Machine Learning, Bioengineering, Robotics, Wearable Devices\nCutting-edge science delivered direct to your inbox.\nJoin the Harvard SEAS mailing list.","confidence":0.9,"diagnostics_url":"/api/diagnose?url=https%3A//seas.harvard.edu/news/can-ai-make-wearable-technologies-and-assistive-devices-more-helpful","quality_bucket":"high","failure_kind":"none","retryable":false,"quality_reason":"High confidence: full text extraction produced 5819 characters.","quality_profile":{"profile_version":"extraction_quality.v2","bucket":"high","confidence":0.9,"failure_kind":"none","retryable":false,"retry_after_attempts":0,"reason":"High confidence: full text extraction produced 5819 characters.","operator_guidance":{"severity":"ok","recommended_action":"trust_full_text","next_step":"Use the extracted full text as the primary article source.","operator_label":"Ready","can_retry":false,"can_use_summary":false,"diagnostics_required":false},"content_depth":{"contract_version":"content_depth.v1","category":"full_text","label":"Full text","has_full_text":true,"has_summary":true,"content_length":5819,"summary_length":238,"usable_text_length":5819,"source_field":"content"},"legacy_collapsed":false,"signals":{"extract_state":"ok","extract_error":null,"extract_retries":0,"content_length":5819,"summary_length":238}},"tags":[]},"fallback_formats":["markdown","json","html"],"actions":{"read":"/item/44507","export_markdown":"/api/items/44507/export?format=markdown","export_json":"/api/items/44507/export?format=json","diagnose":"/api/diagnose?url=https%3A//seas.harvard.edu/news/can-ai-make-wearable-technologies-and-assistive-devices-more-helpful"},"formats":{"full":{"id":44507,"title":"Can AI Make Wearable Technologies and Assistive Devices More Helpful? - Harvard University","url":"https://seas.harvard.edu/news/can-ai-make-wearable-technologies-and-assistive-devices-more-helpful","source":"Harvard University","author":null,"published_at":"2026-07-23T13:12:14+00:00","locale":"en","topic":"ai","tags":[],"excerpt":"News\nPatrick Slade is an Assistant Professor of Bioengineering at the Harvard John A. His research combines wearable robotics, biomechanics, sensing, and artificial intelligence to help people move more easily and safely in everyday life.","full_text":"News\nPatrick Slade is an Assistant Professor of Bioengineering at the Harvard John A. Paulson School of Engineering and Applied Sciences (SEAS). His research combines wearable robotics, biomechanics, sensing, and artificial intelligence to help people move more easily and safely in everyday life. His lab develops technologies that can measure human movement, adapt assistance to individual users, and support people with mobility or navigation challenges. The following Q&A was developed from interviews with Slade. It has been edited for clarity, length, and context.\nQ: How does AI improve wearable technologies and assistive devices?\nA: One thing we have learned in wearable robotics is that putting a motor on someone does not necessarily make it easier for them to move. In some cases, it can actually make movement harder because the device is not working in harmony with the person.\nWe all move a little differently. People vary in their strength, balance, motor control, and movement patterns, and those differences become even more important in patient populations. A device that helps one person may not help another in the same way.\nAI gives us tools to better understand those differences. We can combine wearable sensors with machine-learning models to estimate things that are difficult to measure outside the lab, such as energy expenditure, walking speed, movement asymmetry, or joint loading. We can then use that information to personalize the assistance — adjusting when it is delivered, how much is provided, and what outcome we are trying to improve.\nQ: What are the limitations of current wearables, like smartwatches?\nA: Consumer wearables are very good at collecting data, but some of the metrics they report can be surprisingly inaccurate. Estimates of energy expenditure, or calories burned, can sometimes have errors on the order of 40 to 80 percent.\nPart of the problem is that many devices rely on indirect signals such as heart rate or wrist motion. Those signals can be useful, but they do not always reflect the mechanical work the body is doing. When you walk or run, much of the energy expenditure comes from the muscles in your legs, not from the movement of your wrist.\nOur approach is to use signals that are more closely connected to biomechanics. For example, a smartphone carried in a pocket can measure acceleration. We can combine that information with machine-learning models and established principles from physics to estimate meaningful measures such as energy expenditure more accurately.\nThe goal is not simply to collect more data. It is to identify the signals that matter most and use AI in a way that reflects how the body actually works.\nQ: What is the biggest challenge in developing wearable and assistive technologies?\nA: Personalization is one of the central challenges in our research. People vary in their movement patterns, strength, balance, motor control, anatomy, and goals. Those differences become especially important for people who have experienced a stroke, people with knee osteoarthritis or knee pain, older adults, and people with blindness or visual impairment.\nA fixed controller might help one person and hinder another. Instead, we want the technology to learn how a particular person moves and determine what kind of support is most useful.\nFor a wearable robot, that might mean adjusting when assistance is delivered, how much force is applied, or which outcome the system is trying to improve. We might tune the device to reduce energy expenditure, increase walking speed, improve symmetry between the legs, or reduce loading on a painful knee.\nWe also need these systems to adapt outside controlled laboratory settings. People walk at different speeds, change direction, climb stairs, encounter uneven ground, and perform activities that may not appear in a training dataset. Our existing knowledge of human movement can help make the technology more robust and trustworthy.\nQ: Can you give examples of AI-powered assistive technologies in practice?\nA: One example is our work with people who have experienced a stroke. We can use wearable sensors and AI to estimate walking speed and asymmetry between the paretic and non-paretic legs. That information can help us personalize a wearable robot and determine how the device should assist the person.\nAnother application involves people with knee osteoarthritis or knee pain. In that work, we estimate the load passing through the knee and explore how an assistive device might reduce it.\nWe are also developing navigation technology for people with blindness or visual impairment. The system uses a smartphone camera, GPS, and motion data to identify features such as sidewalks, curb cuts, crosswalks, and obstacles. It then provides audio feedback through open-ear headphones to help guide the user.\nAcross these projects, AI allows the technology to interpret complex information and adapt assistance to the person and the environment.\nQ: What is the future of AI-powered wearable and assistive technologies?\nA. I think it is realistic that, within the next several years, people will be able to buy wearable devices that personalize themselves automatically using AI. These systems could support older adults, people with mobility impairments, workers performing physically demanding tasks, or anyone who wants help remaining active.\nAn e-bike is a useful analogy. It does not replace cycling; it provides enough assistance to make cycling more accessible. Wearable robotics could play a similar role by making movement easier, reducing pain or fatigue, and helping people continue doing the activities that matter to them.\nTopics: AI / Machine Learning, Bioengineering, Robotics, Wearable Devices\nCutting-edge science delivered direct to your inbox.\nJoin the Harvard SEAS mailing list.","reading_time_min":5,"extraction":{"state":"ok","confidence":0.9,"error":null,"explanation":"High confidence: full text extraction produced 5819 characters.","diagnostics_url":"/api/diagnose?url=https%3A//seas.harvard.edu/news/can-ai-make-wearable-technologies-and-assistive-devices-more-helpful","quality_profile":{"profile_version":"extraction_quality.v2","bucket":"high","confidence":0.9,"failure_kind":"none","retryable":false,"retry_after_attempts":0,"reason":"High confidence: full text extraction produced 5819 characters.","operator_guidance":{"severity":"ok","recommended_action":"trust_full_text","next_step":"Use the extracted full text as the primary article source.","operator_label":"Ready","can_retry":false,"can_use_summary":false,"diagnostics_required":false},"content_depth":{"contract_version":"content_depth.v1","category":"full_text","label":"Full text","has_full_text":true,"has_summary":true,"content_length":5819,"summary_length":238,"usable_text_length":5819,"source_field":"content"},"legacy_collapsed":false,"signals":{"extract_state":"ok","extract_error":null,"extract_retries":0,"content_length":5819,"summary_length":238}}},"quality_profile":{"profile_version":"extraction_quality.v2","bucket":"high","confidence":0.9,"failure_kind":"none","retryable":false,"retry_after_attempts":0,"reason":"High confidence: full text extraction produced 5819 characters.","operator_guidance":{"severity":"ok","recommended_action":"trust_full_text","next_step":"Use the extracted full text as the primary article source.","operator_label":"Ready","can_retry":false,"can_use_summary":false,"diagnostics_required":false},"content_depth":{"contract_version":"content_depth.v1","category":"full_text","label":"Full text","has_full_text":true,"has_summary":true,"content_length":5819,"summary_length":238,"usable_text_length":5819,"source_field":"content"},"legacy_collapsed":false,"signals":{"extract_state":"ok","extract_error":null,"extract_retries":0,"content_length":5819,"summary_length":238}},"actions":{"read":"/item/44507","export_markdown":"/api/items/44507/export?format=markdown","export_json":"/api/items/44507/export?format=json","diagnose":"/api/diagnose?url=https%3A//seas.harvard.edu/news/can-ai-make-wearable-technologies-and-assistive-devices-more-helpful"}},"digest":{"id":44507,"title":"Can AI Make Wearable Technologies and Assistive Devices More Helpful? - Harvard University","url":"https://seas.harvard.edu/news/can-ai-make-wearable-technologies-and-assistive-devices-more-helpful","source":"Harvard University","topic":"ai","published_at":"2026-07-23T13:12:14+00:00","excerpt":"News Patrick Slade is an Assistant Professor of Bioengineering at the Harvard John A. His research combines wearable robotics, biomechanics, sensing, and artificial intelligence to help people move more easily and safely in everyday life.","quality_bucket":"high","quality_reason":"High confidence: full text extraction produced 5819 characters.","reading_time_min":5,"cluster_id":null},"card":{"display_title":"Can AI Make Wearable Technologies and Assistive Devices More Helpful? - Harvard University","subtitle":"Harvard University · 2026-07-23","summary":"News Patrick Slade is an Assistant Professor of Bioengineering at the Harvard John A. His research combines wearable robotics, biomechanics, sensing, and artificial intelligence to help people move more easily and…","badges":["quality:high"],"links":{"read":"/item/44507","original":"https://seas.harvard.edu/news/can-ai-make-wearable-technologies-and-assistive-devices-more-helpful","diagnose":"/api/diagnose?url=https%3A//seas.harvard.edu/news/can-ai-make-wearable-technologies-and-assistive-devices-more-helpful"},"quality_warning":null},"export":{"title":"Can AI Make Wearable Technologies and Assistive Devices More Helpful? - Harvard University","url":"https://seas.harvard.edu/news/can-ai-make-wearable-technologies-and-assistive-devices-more-helpful","summary":"News\nPatrick Slade is an Assistant Professor of Bioengineering at the Harvard John A. His research combines wearable robotics, biomechanics, sensing, and artificial intelligence to help people move more easily and safely in everyday life.","source":"Harvard University","date":"2026-07-23T13:12:14+00:00","content":"News\nPatrick Slade is an Assistant Professor of Bioengineering at the Harvard John A. Paulson School of Engineering and Applied Sciences (SEAS). His research combines wearable robotics, biomechanics, sensing, and artificial intelligence to help people move more easily and safely in everyday life. His lab develops technologies that can measure human movement, adapt assistance to individual users, and support people with mobility or navigation challenges. The following Q&A was developed from interviews with Slade. It has been edited for clarity, length, and context.\nQ: How does AI improve wearable technologies and assistive devices?\nA: One thing we have learned in wearable robotics is that putting a motor on someone does not necessarily make it easier for them to move. In some cases, it can actually make movement harder because the device is not working in harmony with the person.\nWe all move a little differently. People vary in their strength, balance, motor control, and movement patterns, and those differences become even more important in patient populations. A device that helps one person may not help another in the same way.\nAI gives us tools to better understand those differences. We can combine wearable sensors with machine-learning models to estimate things that are difficult to measure outside the lab, such as energy expenditure, walking speed, movement asymmetry, or joint loading. We can then use that information to personalize the assistance — adjusting when it is delivered, how much is provided, and what outcome we are trying to improve.\nQ: What are the limitations of current wearables, like smartwatches?\nA: Consumer wearables are very good at collecting data, but some of the metrics they report can be surprisingly inaccurate. Estimates of energy expenditure, or calories burned, can sometimes have errors on the order of 40 to 80 percent.\nPart of the problem is that many devices rely on indirect signals such as heart rate or wrist motion. Those signals can be useful, but they do not always reflect the mechanical work the body is doing. When you walk or run, much of the energy expenditure comes from the muscles in your legs, not from the movement of your wrist.\nOur approach is to use signals that are more closely connected to biomechanics. For example, a smartphone carried in a pocket can measure acceleration. We can combine that information with machine-learning models and established principles from physics to estimate meaningful measures such as energy expenditure more accurately.\nThe goal is not simply to collect more data. It is to identify the signals that matter most and use AI in a way that reflects how the body actually works.\nQ: What is the biggest challenge in developing wearable and assistive technologies?\nA: Personalization is one of the central challenges in our research. People vary in their movement patterns, strength, balance, motor control, anatomy, and goals. Those differences become especially important for people who have experienced a stroke, people with knee osteoarthritis or knee pain, older adults, and people with blindness or visual impairment.\nA fixed controller might help one person and hinder another. Instead, we want the technology to learn how a particular person moves and determine what kind of support is most useful.\nFor a wearable robot, that might mean adjusting when assistance is delivered, how much force is applied, or which outcome the system is trying to improve. We might tune the device to reduce energy expenditure, increase walking speed, improve symmetry between the legs, or reduce loading on a painful knee.\nWe also need these systems to adapt outside controlled laboratory settings. People walk at different speeds, change direction, climb stairs, encounter uneven ground, and perform activities that may not appear in a training dataset. Our existing knowledge of human movement can help make the technology more robust and trustworthy.\nQ: Can you give examples of AI-powered assistive technologies in practice?\nA: One example is our work with people who have experienced a stroke. We can use wearable sensors and AI to estimate walking speed and asymmetry between the paretic and non-paretic legs. That information can help us personalize a wearable robot and determine how the device should assist the person.\nAnother application involves people with knee osteoarthritis or knee pain. In that work, we estimate the load passing through the knee and explore how an assistive device might reduce it.\nWe are also developing navigation technology for people with blindness or visual impairment. The system uses a smartphone camera, GPS, and motion data to identify features such as sidewalks, curb cuts, crosswalks, and obstacles. It then provides audio feedback through open-ear headphones to help guide the user.\nAcross these projects, AI allows the technology to interpret complex information and adapt assistance to the person and the environment.\nQ: What is the future of AI-powered wearable and assistive technologies?\nA. I think it is realistic that, within the next several years, people will be able to buy wearable devices that personalize themselves automatically using AI. These systems could support older adults, people with mobility impairments, workers performing physically demanding tasks, or anyone who wants help remaining active.\nAn e-bike is a useful analogy. It does not replace cycling; it provides enough assistance to make cycling more accessible. Wearable robotics could play a similar role by making movement easier, reducing pain or fatigue, and helping people continue doing the activities that matter to them.\nTopics: AI / Machine Learning, Bioengineering, Robotics, Wearable Devices\nCutting-edge science delivered direct to your inbox.\nJoin the Harvard SEAS mailing list.","confidence":0.9,"diagnostics_url":"/api/diagnose?url=https%3A//seas.harvard.edu/news/can-ai-make-wearable-technologies-and-assistive-devices-more-helpful","quality_bucket":"high","failure_kind":"none","retryable":false,"quality_reason":"High confidence: full text extraction produced 5819 characters.","quality_profile":{"profile_version":"extraction_quality.v2","bucket":"high","confidence":0.9,"failure_kind":"none","retryable":false,"retry_after_attempts":0,"reason":"High confidence: full text extraction produced 5819 characters.","operator_guidance":{"severity":"ok","recommended_action":"trust_full_text","next_step":"Use the extracted full text as the primary article source.","operator_label":"Ready","can_retry":false,"can_use_summary":false,"diagnostics_required":false},"content_depth":{"contract_version":"content_depth.v1","category":"full_text","label":"Full text","has_full_text":true,"has_summary":true,"content_length":5819,"summary_length":238,"usable_text_length":5819,"source_field":"content"},"legacy_collapsed":false,"signals":{"extract_state":"ok","extract_error":null,"extract_retries":0,"content_length":5819,"summary_length":238}},"tags":[],"format_contract_version":"news_item_formats.v1"}}}