AI RESEARCH

Echo Planning for Autonomous Driving: From Current Observations to Future Trajectories and Back

arXiv CS.CV

ArXi:2505.18945v2 Announce Type: replace Modern end-to-end autonomous driving systems suffer from a critical limitation: their planners lack mechanisms to enforce temporal consistency between predicted trajectories and evolving scene dynamics. This absence of self-supervision allows early prediction errors to compound catastrophically over time. We