analiza aiqbench
This research introduces AlignDrive, a novel framework that couples lateral path planning with longitudinal speed decisions to improve safety and coordination in autonomous driving. By reformulating the problem as a path-conditioned reasoning process and utilizing data augmentation for rare edge cases, the method achieves state-of-the-art performance on rigorous benchmarks like Bench2Drive and Fail2Drive. The work represents significant progress in solving the critical challenge of suboptimal agent interaction that often plagues current parallel planning architectures.
AlignDrive: Aligned Lateral-Longitudinal Planning for End-to-End Autonomous Driving
arXiv:2601.01762v3 Announce Type: replace Abstract: Practical autonomous driving requires models that generalize by reasoning through spatial-temporal possibilities to exclude unsafe outcomes. While state-of-the-art (SOTA) methods use parallel planning architectures, they fail to explicitly couple speed decisions with agent behavior along the driving path, leading to suboptimal coordination. To address this, we propose a cascaded framework that transforms longitudinal planning from an independent prediction task into a path-conditioned reasoning process. On the model side, we introduce an anchor-based regression design that conditions longitudinal prediction on the lateral drive path, and reformulate longitudinal planning as 1D displacement prediction along the path. This reduces geometric uncertainty and sharpens the model's focus on interaction-driven dynamics. On the data side, we introduce a planning-oriented data augmentation strategy that simulates rare safety-critical events by programmatically inserting agents and relabeling longitudinal targets to enforce collision avoidance. Evaluated on the challenging Bench2Drive benchmark, our method achieves SOTA performance with a driving score of 89.07 and a success rate of 73.18%, demonstrating significantly improved coordination and safety. Further evaluation on Fail2Drive confirms strong generalization to rare edge cases where parallel formulations typically fail. Project page:https://yanhaowu.github.io/AlignDrive/.
Abstract:Practical autonomous driving requires models that generalize by reasoning through spatial-temporal possibilities to exclude unsafe outcomes. While state-of-the-art (SOTA) methods use parallel planning architectures, they fail to explicitly couple speed decisions with agent behavior along the driving path, leading to suboptimal coordination. To address this, we propose a cascaded framework that transforms longitudinal planning from an independent prediction task into a path-conditioned reasoning process. On the model side, we introduce an anchor-based regression design that conditions longitudinal prediction on the lateral drive path, and reformulate longitudinal planning as 1D displacement prediction along the path. This reduces geometric uncertainty and sharpens the model's focus on interaction-driven dynamics. On the data side, we introduce a planning-oriented data augmentation strategy that simulates rare safety-critical events by programmatically inserting agents and relabeling longitudinal targets to enforce collision avoidance. Evaluated on the challenging Bench2Drive benchmark, our method achieves SOTA performance with a driving score of 89.07 and a success rate of 73.18%, demonstrating significantly improved coordination and safety. Further evaluation on Fail2Drive confirms strong generalization to rare edge cases where parallel formulations typically fail. Project page:this https URL.
Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
arXiv:2601.01762 [cs.RO]
(or arXiv:2601.01762v3 [cs.RO] for this version)
Text integral sub licența deschisă a publicației · 199 cuvinte
Subiecte conexe
AlignDrive: Aligned Lateral-Longitudinal Planning for End-to-End Autonomous Driving
arXiv · 30 sept. 2026
Concrete Evaluations to Investigate the OpenAI Model That Hacked Hugging Face
AI Alignment Forum · 3 aug. 2026
Problems of Proliferation
LessWrong · 29 sept. 2026
[AINews] Reality Checks on AI News (Yegge shuts down Gas Town, Databricks’ +60% Astra cost)
Latent Space · 17 sept. 2026