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

Planning an optimal route in a complex environment requires efficientreasoning about the surrounding scene. While human drivers prioritize importantobjects and ignore details not relevant to the decision, learning-basedplanners typically extract features from dense, high-dimensional gridrepresentations containing all vehicle and road context information. In thispaper, we propose PlanT, a novel approach for planning in the context ofself-driving that uses a standard transformer architecture. PlanT is based onimitation learning with a compact object-level input representation. On theLongest6 benchmark for CARLA, PlanT outperforms all prior methods (matching thedriving score of the expert) while being 5.3x faster than equivalentpixel-based planning baselines during inference. Combining PlanT with anoff-the-shelf perception module provides a sensor-based driving system that ismore than 10 points better in terms of driving score than the existing state ofthe art. Furthermore, we propose an evaluation protocol to quantify the abilityof planners to identify relevant objects, providing insights regarding theirdecision-making. Our results indicate that PlanT can focus on the most relevantobject in the scene, even when this object is geometrically distant.

PlanT: Explainable Planning Transformers via Object-Level Representations