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

Jintao Sun, Hu Zhang, Gangyi Ding, Zhedong Zheng

Keywords: End-to-End, Autonomous Driving, Planing, Temporal

Abstract: 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 introduce Echo Planning (**EchoP**), a new self-correcting framework that establishes an end-to-end Current → Future → Current (CFC) cycle to harmonize trajectory prediction with scene coherence. Our key insight is that plausible future trajectories must be bi-directionally consistent, \ie, not only generated from current observations but also capable of reconstructing them. The CFC mechanism first predicts future trajectories from the Bird’s-Eye-View (BEV) scene representation, then inversely maps these trajectories back to estimate the current BEV state. By enforcing consistency between the original and reconstructed BEV representations through a cycle loss, the framework intrinsically penalizes physically implausible or misaligned trajectories. Experiments on nuScenes show that the proposed method yields competitive performance, reducing L2 error (Avg) by -0.04 m and collision rate by -0.12\% compared to one-shot planners. The approach also scales to closed-loop evaluation, i.e., Bench2Drive, attaining a 26.52\% success rate. Notably, EchoP requires no additional supervision: the CFC cycle acts as an inductive bias that stabilizes long-horizon planning. Overall, EchoP offers a simple, deployable pathway to improve reliability in safety-critical autonomous driving.

Primary Area: applications to robotics, autonomy, planning

Submission Number: 3118