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

Large Language Models (LLMs) pre-trained on internet-scale datasets haveshown impressive capabilities in code understanding, synthesis, and generalpurpose question-and-answering. Key to their performance is the substantialprior knowledge acquired during training and their ability to reason overextended sequences of symbols, often presented in natural language. In thiswork, we aim to harness the extensive long-term reasoning, natural languagecomprehension, and the available prior knowledge of LLMs for increasedresilience and adaptation in autonomous mobile robots. We introduce REAL, anapproach for REsilience and Adaptation using LLMs. REAL provides a strategy toemploy LLMs as a part of the mission planning and control framework of anautonomous robot. The LLM employed by REAL provides (i) a source of priorknowledge to increase resilience for challenging scenarios that the system hadnot been explicitly designed for; (ii) a way to interpret natural-language andother log/diagnostic information available in the autonomy stack, for missionplanning; (iii) a way to adapt the control inputs using minimal user-providedprior knowledge about the dynamics/kinematics of the robot. We integrate REALin the autonomy stack of a real multirotor, querying onboard an offboard LLM at0.1-1.0 Hz as part the robot's mission planning and control feedback loops. Wedemonstrate in real-world experiments the ability of the LLM to reduce theposition tracking errors of a multirotor under the presence of (i) errors inthe parameters of the controller and (ii) unmodeled dynamics. We also show(iii) decision making to avoid potentially dangerous scenarios (e.g., robotoscillates) that had not been explicitly accounted for in the initial promptdesign.

REAL: Resilience and Adaptation using Large Language Models on Autonomous Aerial Robots