Work

D3.1 - Design of Algorithms for Trustable Social Navigation

Year: 2024

Type: article

Abstract: We describe the design and implementation of a library of navigation algorithms and tools to test and analyze them. The design is based on the requirements from five user categories represented in the project but also targets the broader robotics community. The library is modular and extensible from C++ and Python. Tools comprise a simulator to run large-scale offline experiments, a Virtual Reality extension to test with humans-in-the-loop, and an interface with machine learning libraries.

Source: Zenodo (CERN European Organization for Nuclear Research)

DOI: 10.5281/zenodo.14864555

Author: Dalle Molle Institute for Artificial Intelligence Research

Institution: University of Applied Sciences and Arts of Southern Switzerland

Language: English

Topic: Reinforcement Learning in Robotics

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: European Commission

Award: REliable & eXplAinable Swarm Intelligence for People with Reduced mObility