Echo planning for autonomous driving: From current observations to future trajectories and back

Authors: Jintao Sun, Hu Zhang, Gangyi Ding, Zhedong Zheng

Published in IEEE Transactions on Multimedia (TMM), 2026

Recommended citation: Jintao Sun, Hu Zhang, Gangyi Ding, Zhedong Zheng, "Echo planning for autonomous driving: From current observations to future trajectories and back." TMM, 2026. DOI: 10.1109/TMM.2026.3713776
Download PDF: https://zdzheng.xyz/files/2026/TMM_jintao_planning.pdf

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 should be bi-directionally consistent, i.e., 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. Moreover, EchoP seamlessly extends to closed-loop evaluation, i.e., Bench2Drive, attaining a 26.54\% 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.

@article{sun2026echo,
author = "Sun, Jintao and Zhang, Hu and Ding, Gangyi and Zheng, Zhedong",
title = "Echo planning for autonomous driving: From current observations to future trajectories and back",
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 should be bi-directionally consistent, i.e., 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. Moreover, EchoP seamlessly extends to closed-loop evaluation, i.e., Bench2Drive, attaining a 26.54\\% 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.",
url = "https://zdzheng.xyz/files/2026/TMM\_jintao\_planning.pdf",
doi = "10.1109/TMM.2026.3713776",
funding = "FDCT/0043/2025/RIA1, 2025A1515012281, BZ2025029",
journal = "TMM",
year = "2026" }