Planning-aligned Token Compression for Long-Context Autonomous Driving
NVIDIA Research(NVIDIA研究);School of Computing and Data Science, The University of Hong Kong(计算与数据科学学院,香港大学)
Zhixuan Liang, Yuxiao Chen, Yurong You, Peter Karkus, Wenhao Ding, Boyi Li, Alexander Popov, Yan Wang, Maximilian Igl, Yiming Li, Danfei Xu, Nikolai Smolyanskiy… 展开作者
Zhixuan Liang, Yuxiao Chen, Yurong You, Peter Karkus, Wenhao Ding, Boyi Li, Alexander Popov, Yan Wang, Maximilian Igl, Yiming Li, Danfei Xu, Nikolai Smolyanskiy, Boris Ivanovic, Ping Luo, Marco Pavone
Monolithic vision-action models represent an emerging paradigm in autonomous driving. However, this architecture produces token sequences that quickly exceed real-time computational budgets when encoding extended temporal context for complex interactions. While approaches like linear transformers and external memory try to make the context lightweight, token compression is most compatible with the architecture as it requires no backbone modifications. Yet existing compression adopts rule-based heuristics like temporal decay, decoupled from planning, risking loss of decision-critical information. We propose COMPACT-VA, a planning-aligned working memory framework built on conditional VQ-VAE, compressing extended context into bounded representations. Compression is conditioned on both historical trajectory and a learned planning intent that the posterior encoder distills from future trajectories during training, while the prior encoder learns to predict it from compressed observations. The compressed memory, concatenated with the predicted latent, feeds the policy for end-to-end optimization, planning with retained decision-critical information. We evaluate on high-signal dynamic scenarios where historical context is most critical for behavior correctness (e.g., stop, yield, or proceed), and accordingly design behavioral metrics. Under comparable token budgets, we achieve $>$6% improvement (68.3%) on success rates with consistent gains across metrics. Ablations validate planning-aligned coupling effectiveness. Closed-loop evaluation confirms that COMPACT-VA maintained general driving performance with 3.3* speedup and 2.7* memory reduction over uncompressed processing.
AlignDrive: Aligned Lateral-Longitudinal Planning for End-to-End Autonomous Driving
School of Software Engineering, XJTU(软件工程学院,西安交通大学);Horizon Robotics;Shenzhen Loop Area Institute(深圳河套学院);University of Chinese Academy of Sciences(中国科学院大学)
本文提出一种 cascaded 框架,通过将纵向规划转化为路径条件推理过程,提升自动驾驶的协调性和安全性。方法引入锚点回归设计和规划导向的数据增强策略,实现在 Bench2Drive 上达到 SOTA 性能。
WALT: Learning World-Model-Aligned Latent Trajectories for Autonomous Driving
The Hong Kong University of Science and Technology(香港科技大学);Horizon Robotics(地平线机器人);The Chinese University of Hong Kong(香港中文大学);Nanjing University of Posts and Telecommunications(南京邮电大学);Nankai University(南开大学)
Future-Aware Flow Planning for Safe UAV Target Following
Stockholm University(斯德哥尔摩大学);Peking University(北京大学);Beijing Normal-Hong Kong Baptist University(北京师范大学-香港浸会大学联合国际学院);Guangdong Provincial/Zhuhai Key Laboratory of IRADS(广东省/珠海市智能机器人先进感知与决策系统重点实验室)
FeaXDrive: Feasibility-aware Trajectory-Centric Diffusion Planning for End-to-End Autonomous Driving
College of Automotive and Energy Engineering, Tongji University(同济大学汽车与能源工程学院);College of Transportation Engineering, Tongji University(同济大学交通工程学院);School of Mechanical and Aerospace Engineering, Nanyang Technological University(南洋理工大学机械与航空航天工程学院)
Mind and Motion Aligned: A Joint Evaluation IsaacSim Benchmark for Task Planning and Low-Level Policies in Mobile Manipulation
AIRI;Moscow Institute of Physics and Technology (MIPT)(莫斯科物理技术学院);Lomonosov Moscow State University(罗蒙诺索夫莫斯科国立大学);Sberbank, Robotics Center(Sberbank机器人中心);Skoltech
本文提出 Kitchen-R 基准,在 Isaac Sim 数字孪生厨房环境中统一评估任务规划与底层控制,并提供视觉语言模型规划、扩散策略控制及轨迹采集系统,支持独立与集成评估,弥补具身 AI 中语言引导机器人整体评测的空白。
Communication-Aware Map Compression for Online Path-Planning: A Rate-Distortion Approach
Department of Aerospace Engineering of Georgia Institute of Technology(佐治亚理工学院航空航天工程系);Department of Electrical and Computer Engineering, University of North Carolina at Charlotte(北卡罗来纳大学夏洛特分校电气与计算机工程系)