Online User Assessment for Minimal Intervention During Task-Based Robotic Assistance

The International Journal of Robotics Research

Kalinowska

Dewald

et al. 2020

Self Cite

Despite the fact that robotic platforms can provide both consistent practice and objective assessments of users over the course of their training, there are relatively few instances where physical human–robot interaction has been significantly more effective than unassisted practice or human-mediated training. This article describes a hybrid shared control robot, which enhances task learning through kinesthetic feedback. The assistance assesses user actions using a task-specific evaluation criterion and selectively accepts or rejects them at each time instant. Through two human subject studies (total [Formula: see text]), we show that this hybrid approach of switching between full transparency and full rejection of user inputs leads to increased skill acquisition and short-term retention compared with unassisted practice. Moreover, we show that the shared control paradigm exhibits features previously shown to promote successful training. It avoids user passivity by only rejecting user actions and allowing failure at the task. It improves performance during assistance, providing meaningful task-specific feedback. It is sensitive to initial skill of the user and behaves as an “assist-as-needed” control scheme, adapting its engagement in real time based on the performance and needs of the user. Unlike other successful algorithms, it does not require explicit modulation of the level of impedance or error amplification during training and it is permissive to a range of strategies because of its evaluation criterion. We demonstrate that the proposed hybrid shared control paradigm with a task-based minimal intervention criterion significantly enhances task-specific training.

Section: Prior Workmentioning

confidence: 74%

Section: Prior Workmentioning

confidence: 99%

Section: Hybrid Shared Control Adapts To Initial Skillmentioning

confidence: 99%

See 1 more Smart Citation

Task-based hybrid shared control for training through forceful interaction

The International Journal of Robotics Research

Kalinowska

Dewald

et al. 2020

Self Cite

“…Participants were each given 3 sets of 30 30-second attempts to invert the pole from its resting state to the unstable equilibrium. The data from this experimentdetails of which can be found in [38] and [39]-are used as the novice task demonstrations in this work.…”

Section: B Experimental Platformsmentioning

confidence: 99%

Ergodic imitation: Learning from what to do and what not to do

Kalinowska

Prabhakar

2021 IEEE International Conference on Robotics and Automation (ICRA)

et al. 2021

Self Cite

With growing access to versatile robotics, it is beneficial for end users to be able to teach robots tasks without needing to code a control policy. One possibility is to teach the robot through successful task executions. However, nearoptimal demonstrations of a task can be difficult to provide and even successful demonstrations can fail to capture task aspects key to robust skill replication. Here, we propose a learning from demonstration (LfD) approach that enables learning of robust task definitions without the need for near-optimal demonstrations. We present a novel algorithmic framework for learning tasks based on the ergodic metric-a measure of information content in motion. Moreover, we make use of negative demonstrations-demonstrations of what not to do-and show that they can help compensate for imperfect demonstrations, reduce the number of demonstrations needed, and highlight crucial task elements improving robot performance. In a proofof-concept example of cart-pole inversion, we show that negative demonstrations alone can be sufficient to successfully learn and recreate a skill. Through a human subject study with 24 participants, we show that consistently more information about a task can be captured from combined positive and negative (posneg) demonstrations than from the same amount of just positive demonstrations. Finally, we demonstrate our learning approach on simulated tasks of target reaching and table cleaning with a 7-DoF Franka arm. Our results point towards a future with robust, data-efficient LfD for novice users.

“…A filter-based assistance algorithm proposed in [30] for pure noise inputs, and adapted for user input in [31] and [32] was applied to a virtual cart-pendulum inversion task on the NACT-3D. The assistance physically filters the user's inputsaccelerations in this case-such that their actions are always in the direction of an optimal control policy calculated in real time.…”

Section: A Human Subjects Datasetmentioning

confidence: 99%

Dynamical System Segmentation for Information Measures in Motion

Berrueta

Pervan

IEEE Robot. Autom. Lett.

et al. 2019

Self Cite

Motions carry information about the underlying task being executed. Previous work in human motion analysis suggests that complex motions may result from the composition of fundamental submovements called movemes. The existence of finite structure in motion motivates information-theoretic approaches to motion analysis and robotic assistance. We define task embodiment as the amount of task information encoded in an agent's motions. By decoding task-specific information embedded in motion, we can use task embodiment to create detailed performance assessments. We extract an alphabet of behaviors comprising a motion without a priori knowledge using a novel algorithm, which we call dynamical system segmentation. For a given task, we specify an optimal agent, and compute an alphabet of behaviors representative of the task. We identify these behaviors in data from agent executions, and compare their relative frequencies against that of the optimal agent using the Kullback-Leibler divergence. We validate this approach using a dataset of human subjects (n = 53) performing a dynamic task, and under this measure find that individuals receiving assistance better embody the task. Moreover, we find that task embodiment is a better predictor of assistance than integrated mean-squarederror.