The paper introduces Feel‑WM, an off‑road navigation world model that incorporates proprioceptive data to predict both visual scenes and the robot’s physical sensations such as slip, tilt, and shake. By learning a future proprioceptive state and failure risk from the robot’s own experience, the model can evaluate planned trajectories using a separable score that balances goal similarity with predicted failure risk. Experiments on real and simulated off‑road data show that Feel‑WM outperforms visual‑only models in both open‑loop planning and closed‑loop navigation for wheeled and legged robots, and it successfully guides a Husky robot around rough terrain on mountain trails where an end‑to‑end policy fails.
By E-In Son, Dong-Wook Kim, Ji-Hoon Hwang, Kangsun Lee, Jisung Bae, Jung-Taak Kim, Seung-Woo Seo
The paper introduces CoLT-Drive, a 3,536-sample counterfactual long‑tail benchmark for evaluating decision‑level driving affordance prediction, which tests whether models can infer how rare objects affect an ego vehicle’s high‑level actions. It also proposes KPA, a knowledge‑preserving adaptation framework that combines structured prompting, expert merging, and a regime‑aware LoRA mixture‑of‑experts module to improve small VLMs on driving tasks. Experiments show KPA achieves 60.8% pair accuracy on CoLT‑Drive, outperforming the Qwen3‑VL‑2B baseline and LoRA SFT while keeping competitive in‑domain performance.
By Zhengxu Tang, Guofeng Cui, Ziyu Gong, Xiaozhou Zhang, Ruifeng Deng, Chengzhi Qi, Ke Chen, Sachin Patil, Tianjun Xiao, Langechuan Liu, Pichao Wang
The paper introduces Safe Contrastive Reinforcement Learning (Safe-CRL), a method that corrects bias in contrastive RL caused by failure-terminated Markov decision processes. By applying mass-weighted InfoNCE and a log-survival-mass score, Safe-CRL uses only a one-bit failure signal to improve survival and goal-reaching performance across twelve robot navigation and locomotion tasks. The approach demonstrates complex failure-avoidance behaviors and completes the theoretical foundation of contrastive RL under failure termination.
By Guopeng Li, Yiyang Duan, Yiru Jiao, Chengcheng Xu
arXiv:2609.37070v1 Announce Type: cross
Abstract: Rare but consequential failures can persist in learned locomotion policies for legged robots even when average task performance is high, in part beca...
By Ivan Ovinnikov, Pascal Sutter, Christian Gehring, Jordis Herrmann
arXiv:2609.16368v1 Announce Type: cross
Abstract: Vision-language models (VLMs) can generate routes directly from aerial imagery for off-road navigation, but their predictions provide no indication o...
By Ghazal Farhani, Shabnam Shabani
arXiv:2603.28029v3 Announce Type: replace
Abstract: Criticality metrics such as time-to-collision (TTC) quantify collision urgency but do not distinguish the operational consequences of false-positiv...
By Sharang Kaul, Simon Bultmann, Mario Berk, Abhinav Valada
arXiv:2606. 25127v1 Announce Type: new Abstract: We investigate how reward design shapes the internal attention patterns of reinforcement learning agents trained for autonomous driving.
By Mohamed Benabdelouahad, Ahmed Djalal Hacini, Nadir Farhi, Aissa Boulmerka
arXiv:2607. 18200v1 Announce Type: cross Abstract: Robots in cluttered indoor spaces often fail not because they cannot generate collision-free paths, but because a fixed safety margin is mis-calibrated: conservative margins cause detours and timeouts, while permissive margins lead to near-boundary shortcuts under perception bias.
By Junyi Hu, Shuaihang Yuan, Geeta Chandra Raju Bethala, Anthony Tzes, Yi Fang
Uncertainty estimation for Vision-Language-Navigation (VLN) models is a critical task since it can help identify ambiguous and unreliable predictions, enabling agents to make safer navigation decision...
arXiv:2609.39995v2 Announce Type: new
Abstract: Diffusion planners exhibit strong capabilities in generating multimodal trajectories. However, existing methods primarily rely on expert demonstrations...
By Jiaxi Ye, Chunji Lv, Guoren Wang, Changsheng Li
arXiv:2608.25757v4 Announce Type: replace-cross
Abstract: Large-scale vision--language--action (VLA) policies have advanced generalist robot control, yet most remain stimulus-to-action black boxes: a...
By Jin Lou, Zhiyuan Jing, Xupeng Wang, Andong Chen, Xingdong Zhu, Yuexuan Li, Yuan Xu, Zhijie Zhu, Yingwei Ji, Wenpeng Nie, Renxing Feng, Liangliang Chen, Ying Chu, Jingyi Li, Jinyan Liu, Zhiqi Song, Jingxuan Zhu, Jidong Zhang, Yufei Liu, Boyang Xing, Lei Jiang, Yan Cui, Hongming Li, Yuchen Zhu
arXiv:2609.21486v1 Announce Type: new
Abstract: Multimodal trajectory prediction improves behavioral coverage in end-to-end autonomous driving, but existing methods remain limited by sparse scene rep...
By Jiaxing Chen, Hengduo Zou, YuKai Qin, Yiren Zhao, Lidong Yu, Bolin Gao