Continuous and Unified Modeling of Joint Kinematics for Multiple Activities
Intuitive control of powered prosthetic lower limbs is still an open-ended research goal. Current controllers employ discrete locomotion modes for well-defined and frequently encountered scenarios such as stair ascent, stair descent, or ramps. Non-standard movements such as <bold>side-shufflin...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9765480/ |
| _version_ | 1818201797210144768 |
|---|---|
| author | Vijeth Rai Abhishek Sharma David Boe Pornthep Preechayasomboon Eric Rombokas |
| author_facet | Vijeth Rai Abhishek Sharma David Boe Pornthep Preechayasomboon Eric Rombokas |
| author_sort | Vijeth Rai |
| collection | DOAJ |
| description | Intuitive control of powered prosthetic lower limbs is still an open-ended research goal. Current controllers employ discrete locomotion modes for well-defined and frequently encountered scenarios such as stair ascent, stair descent, or ramps. Non-standard movements such as <bold>side-shuffling into cars and avoiding obstacles</bold> are challenging to powered limb users. Human locomotion is a continuous motion comprising rhythmic and non-rhythmic movements, fluidly adapting to the environment. It exhibits strong inter-joint coordination and the movement of a single joint can be largely predicted based on the movement of the rest of the body. We explore a continuous and unified kinematics estimation strategy for a wide variety of movements without the need for labeled examples. Our data-driven approach uses natural body motion from the intact limbs and trunk to generate a kinematic reference trajectory for prosthetic joints. Wearable sensors were worn by 63 subjects without disabilities to record full-body kinematics during typical scenarios (flat ground and stairs), and non-rhythmic and atypical movements (side shuffles, weaving through cones, backward walking). A Recurrent Neural Network (RNN) was trained to predict right ankle and knee kinematics from the kinematics of other joints as inputs. Results were assessed on 3 different test subjects previously unseen by the network. All predictions had a RMSE of less than 7.5 degrees and a high correlation across activities. These offline predictions were robust to subject-specific variations such as walking speed and step length. Additionally, to test the feasibility of using a data-driven reference towards prosthetic control in real-time, a systems test was designed with a single participant. The controller acquired live kinematics, generated predictions using a pre-trained neural network, and demonstrated the capability to actuate the knee joint of a powered prosthesis for the treadmill walking task. |
| first_indexed | 2024-12-12T02:59:16Z |
| format | Article |
| id | doaj.art-9c95cb80c82b44c5a4feb135a7f6b683 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-12T02:59:16Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-9c95cb80c82b44c5a4feb135a7f6b6832022-12-22T00:40:40ZengIEEEIEEE Access2169-35362022-01-0110475094752310.1109/ACCESS.2022.31712469765480Continuous and Unified Modeling of Joint Kinematics for Multiple ActivitiesVijeth Rai0https://orcid.org/0000-0002-2277-3130Abhishek Sharma1https://orcid.org/0000-0001-6666-2179David Boe2Pornthep Preechayasomboon3Eric Rombokas4https://orcid.org/0000-0001-8523-1913Department of Electrical and Computer Engineering, University of Washington, Seattle, WA, USADepartment of Mechanical Engineering, University of Washington, Seattle, WA, USADepartment of Electrical and Computer Engineering, University of Washington, Seattle, WA, USADepartment of Mechanical Engineering, University of Washington, Seattle, WA, USADepartment of Electrical and Computer Engineering, University of Washington, Seattle, WA, USAIntuitive control of powered prosthetic lower limbs is still an open-ended research goal. Current controllers employ discrete locomotion modes for well-defined and frequently encountered scenarios such as stair ascent, stair descent, or ramps. Non-standard movements such as <bold>side-shuffling into cars and avoiding obstacles</bold> are challenging to powered limb users. Human locomotion is a continuous motion comprising rhythmic and non-rhythmic movements, fluidly adapting to the environment. It exhibits strong inter-joint coordination and the movement of a single joint can be largely predicted based on the movement of the rest of the body. We explore a continuous and unified kinematics estimation strategy for a wide variety of movements without the need for labeled examples. Our data-driven approach uses natural body motion from the intact limbs and trunk to generate a kinematic reference trajectory for prosthetic joints. Wearable sensors were worn by 63 subjects without disabilities to record full-body kinematics during typical scenarios (flat ground and stairs), and non-rhythmic and atypical movements (side shuffles, weaving through cones, backward walking). A Recurrent Neural Network (RNN) was trained to predict right ankle and knee kinematics from the kinematics of other joints as inputs. Results were assessed on 3 different test subjects previously unseen by the network. All predictions had a RMSE of less than 7.5 degrees and a high correlation across activities. These offline predictions were robust to subject-specific variations such as walking speed and step length. Additionally, to test the feasibility of using a data-driven reference towards prosthetic control in real-time, a systems test was designed with a single participant. The controller acquired live kinematics, generated predictions using a pre-trained neural network, and demonstrated the capability to actuate the knee joint of a powered prosthesis for the treadmill walking task.https://ieeexplore.ieee.org/document/9765480/Prosthetic limbsbiomechatronicsrehabilitation robotics |
| spellingShingle | Vijeth Rai Abhishek Sharma David Boe Pornthep Preechayasomboon Eric Rombokas Continuous and Unified Modeling of Joint Kinematics for Multiple Activities IEEE Access Prosthetic limbs biomechatronics rehabilitation robotics |
| title | Continuous and Unified Modeling of Joint Kinematics for Multiple Activities |
| title_full | Continuous and Unified Modeling of Joint Kinematics for Multiple Activities |
| title_fullStr | Continuous and Unified Modeling of Joint Kinematics for Multiple Activities |
| title_full_unstemmed | Continuous and Unified Modeling of Joint Kinematics for Multiple Activities |
| title_short | Continuous and Unified Modeling of Joint Kinematics for Multiple Activities |
| title_sort | continuous and unified modeling of joint kinematics for multiple activities |
| topic | Prosthetic limbs biomechatronics rehabilitation robotics |
| url | https://ieeexplore.ieee.org/document/9765480/ |
| work_keys_str_mv | AT vijethrai continuousandunifiedmodelingofjointkinematicsformultipleactivities AT abhisheksharma continuousandunifiedmodelingofjointkinematicsformultipleactivities AT davidboe continuousandunifiedmodelingofjointkinematicsformultipleactivities AT porntheppreechayasomboon continuousandunifiedmodelingofjointkinematicsformultipleactivities AT ericrombokas continuousandunifiedmodelingofjointkinematicsformultipleactivities |