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

Given access to accurate dynamical models, modern planning approaches areeffective in computing feasible and optimal plans for repetitive robotic tasks.However, it is difficult to model the true dynamics of the real world beforeexecution, especially for tasks requiring interactions with objects whoseparameters are unknown. A recent planning approach, CMAX, tackles this problemby adapting the planner online during execution to bias the resulting plansaway from inaccurately modeled regions. CMAX, while being provably guaranteedto reach the goal, requires strong assumptions on the accuracy of the modelused for planning and fails to improve the quality of the solution overrepetitions of the same task. In this paper we propose CMAX++, an approach thatleverages real-world experience to improve the quality of resulting plans oversuccessive repetitions of a robotic task. CMAX++ achieves this by integratingmodel-free learning using acquired experience with model-based planning usingthe potentially inaccurate model. We provide provable guarantees on thecompleteness and asymptotic convergence of CMAX++ to the optimal path cost asthe number of repetitions increases. CMAX++ is also shown to outperformbaselines in simulated robotic tasks including 3D mobile robot navigation wherethe track friction is incorrectly modeled, and a 7D pick-and-place task wherethe mass of the object is unknown leading to discrepancy between true andmodeled dynamics.

CMAX++ : Leveraging Experience in Planning and Execution using Inaccurate Models