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

With the rapidly growing interest in autonomous navigation, the body ofresearch on motion planning and collision avoidance techniques has enjoyed anaccelerating rate of novel proposals and developments. However, the complexityof new techniques and their safety requirements render the bulk of currentbenchmarking frameworks inadequate, thus leaving the need for efficientcomparison techniques unanswered. This work proposes a novel framework based ondeep reinforcement learning for benchmarking the behavior of collisionavoidance mechanisms under the worst-case scenario of dealing with an optimaladversarial agent, trained to drive the system into unsafe states. We describethe architecture and flow of this framework as a benchmarking solution, anddemonstrate its efficacy via a practical case study of comparing thereliability of two collision avoidance mechanisms in response to intentionalcollision attempts.

Adversarial Reinforcement Learning Framework for Benchmarking Collision Avoidance Mechanisms in Autonomous Vehicles