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

As robots are deployed in complex situations, engineers and end users mustdevelop a holistic understanding of their behaviors, capabilities, andlimitations. Some behaviors are directly optimized by the objective function.They often include success rate, completion time or energy consumption. Otherbehaviors -- e.g., collision avoidance, trajectory smoothness or motionlegibility -- are typically emergent but equally important for safe andtrustworthy deployment. Designing an objective which optimizes every aspect ofrobot behavior is hard. In this paper, we advocate for systematic analysis of awide array of behaviors for holistic understanding of robot controllers and, tothis end, propose a framework, RoCUS, which uses Bayesian posterior sampling tofind situations where the robot controller exhibits user-specified behaviors,such as highly jerky motions. We use RoCUS to analyze three controller classes(deep learning models, rapidly exploring random trees and dynamical systemformulations) on two domains (2D navigation and a 7 degree-of-freedom armreaching), and uncover insights to further our understanding of thesecontrollers and ultimately improve their designs.

RoCUS: Robot Controller Understanding via Sampling