Continual Prediction Learning Techniques to Support Users' Grasp Selection on a Multi-Articulating Prosthetic Hand
Bibliographic record
Abstract
Artificial intelligence methods have shown promise for enhancing human-machine interaction, and also for accelerating progress in the field of robotics. Here, we discuss an application case that brings together these two areas of impact: human interaction with a robotic prosthesis. We present preliminary findings that suggest how continual prediction learning methods from the field of reinforcement learning can be used to streamline user selection of different grasping movements of a dexterous robotic hand. Using powered prosthetic hands is particularly challenging for people with amputations due to the disparity between the many possible grasp patterns a device can support, and the limited number of control channels provided by their body. Previous work introduced a machine learning technique called adaptive switching that demonstrates how a robotic prosthesis could learn to predict the modes or functions a user would deploy during their control interactions, and continually optimize the user’s control interface using this learned predictive information. Adaptive switching has only been tested on a desk-mounted arm prosthesis and has not been extended to the contextual case of grasp selection on a prosthetic hand. Our work contributes a first look at how the prediction-learning foundation of adaptive switching can be extended to support grasp selection on a sensorized multi-articulated prosthetic hand with multiple grip patterns. Specifically, we show how generalized value functions, learned in real time via temporal-difference learning, can predict the future activity of individual fingers in a robotic hand. These predictions were shown to accurately anticipate a cascading pattern of finger movements, which shows the capacity for grasp-related adaptive switching. Our findings suggest the scalability of this approach to predict more complex grasp types, and we recommend moving forward to user-in-the-loop studies of adaptive switching for grasping tasks.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".