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

Although planning is a crucial component of the autonomous driving stack,researchers have yet to develop robust planning algorithms that are capable ofsafely handling the diverse range of possible driving scenarios. Learning-basedplanners suffer from overfitting and poor long-tail performance. On the otherhand, rule-based planners generalize well, but might fail to handle scenariosthat require complex driving maneuvers. To address these limitations, weinvestigate the possibility of leveraging the common-sense reasoningcapabilities of Large Language Models (LLMs) such as GPT4 and Llama2 togenerate plans for self-driving vehicles. In particular, we develop a novelhybrid planner that leverages a conventional rule-based planner in conjunctionwith an LLM-based planner. Guided by commonsense reasoning abilities of LLMs,our approach navigates complex scenarios which existing planners struggle with,produces well-reasoned outputs while also remaining grounded through workingalongside the rule-based approach. Through extensive evaluation on the nuPlanbenchmark, we achieve state-of-the-art performance, outperforming all existingpure learning- and rule-based methods across most metrics. Our code will beavailable at https://llmassist.github.io.

LLM-Assist: Enhancing Closed-Loop Planning with Language-Based Reasoning