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

Model-based reinforcement learning (MBRL) techniques have recently yieldedpromising results for real-world autonomous racing using high-dimensionalobservations. MBRL agents, such as Dreamer, solve long-horizon tasks bybuilding a world model and planning actions by latent imagination. Thisapproach involves explicitly learning a model of the system dynamics and usingit to learn the optimal policy for continuous control over multiple timesteps.As a result, MBRL agents may converge to sub-optimal policies if the worldmodel is inaccurate. To improve state estimation for autonomous racing, thispaper proposes a self-supervised sensor fusion technique that combinesegocentric LiDAR and RGB camera observations collected from the F1TENTH Gym.The zero-shot performance of MBRL agents is empirically evaluated on unseentracks and against a dynamic obstacle. This paper illustrates that multimodalperception improves robustness of the world model without requiring additionaltraining data. The resulting multimodal Dreamer agent safely avoided collisionsand won the most races compared to other tested baselines in zero-shothead-to-head autonomous racing.

Sense, Imagine, Act: Multimodal Perception Improves Model-Based Reinforcement Learning for Head-to-Head Autonomous Racing