Reproduce “Investigating Behavior Cloning from Few Demonstrations for Autonomous Driving based on Bird's-Eye View in Simulated Cities” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Eric Aislan Antonelo, Gustavo Claudio Karl Couto, Christian Möller, Pedro Henrique Fernandes
The method uses kernel density estimation to train a driving policy by giving greater weight to less-common expert actions, rather than detecting traffic-light events. In CARLA’s unseen Town02, it achieved 100 ± 0% mean route completion versus 53 ± 18% for standard behavior cloning. This result does not establish real-world performance or that rare traffic-light actions caused the gain.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.