English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this work, we propose a novel shared autonomy framework to operatearticulated robots. We provide strategies to design both the task-orientedhierarchical planning and policy shaping algorithms for efficient human-robotinteractions in context-aware operation of articulated robots. Our frameworkfor interplay between the human and the autonomy, as the participating agentsin the system, is particularly influenced by the ideas from multi-agentsystems, game theory, and theory of mind for a sliding level of autonomy. Weformulate the sequential hierarchical human-in-the-loop decision making processby extending MDPs and Options framework to shared autonomy, and make use ofdeep RL techniques to train an uncertainty-aware shared autonomy policy. Tofine-tune the formulation to a human, we use history of the system states,human actions, and their error with respect to a surrogate optimal model toencode human's internal state embeddings, beyond the designed values, by usingconditional VAEs. We showcase the effectiveness of our formulation fordifferent human skill levels and degrees of cooperativeness by using a casestudy of a feller-buncher machine in the challenging tasks of timberharvesting. Our framework is successful in providing a sliding level ofautonomy from fully autonomous to fully manual, and is particularly successfulin handling a noisy non-cooperative human agent in the loop. The proposedframework advances the state-of-the-art in shared autonomy for operatingarticulated robots, but can also be applied to other domains where autonomousoperation is the ultimate goal.

Hierarchical Planning and Policy Shaping Shared Autonomy for Articulated Robots