9 papers
DR-VLA: Learning Human-Like Quadruped Navigation from Egocentric Web Videos via Domain-Invariant Scene Representations
Jun Tian, Yingjie Niu, Ruo Chen +2
Quadruped robots performing outdoor deliveries must interpret complex scenes, anticipate changes, and navigate in socially compliant ways. Robot demonstrations are costly to collec…
LynxScenes: A Large-Scale Real-World Benchmark for Outdoor Wheel-Legged Robot Perception, Navigation, Imagination and Reconstruction
Jun Tian, Hao Wu, Ruo Chen +5
Wheel-legged robots operating in outdoor spaces shared with humans require accurate perception, socially compliant navigation, future-scene reasoning, and scene reconstruction. How…
From Pixels to Executable Physics: Behavior-Grounded World Models for Embodied Action Consequence Prediction
Ruo Chen, Jiahua Pang, Yingjie Niu +4
In outdoor environments, varying terrain and contact conditions can cause identical action commands to produce different motion outcomes for quadruped robots. Predicting these outc…
SafeVantage: Vantage-Aware Memory for Reliable Embodied Decisions
Sean Hardesty Lewis, Zuyi Guo, Benwang Chen +4
Reliable embodied decisions under partial observability require informative observations and sufficient supporting evidence. However, semantic scores alone do not reveal which view…
PileBelief: Persistent Physical State for Interaction-Driven World Modeling
Hongyi Lin, Song Zhang, Haiquan Liu +3
World models allow robots to anticipate action consequences before execution. This capability is especially valuable in excavation, where each scoop reshapes the terrain and affect…
Physical-Touch Observability from Wrist Wrench in Granular Scooping
Hongyi Lin, Song Zhang, Xubo Liu +1
Mining and earthmoving are important real-world deployment settings for embodied intelligence. Autonomous transport and driving systems have improved substantially, but loading and…
VeriFuse: Bounded Vision-Language Arbitration and Reason-Guided Refinement for Cooperative 3D Perception
Hongyi Lin, Yiyao Liu, Qi Kang +4
Vision-language models (VLMs) have demonstrated strong scene understanding and semantic judgment across diverse tasks, but their appropriate role in cooperative perception remains…
Rethinking Foundation Model Collaboration: Enhancing Specialized Models through Proxy Task Reasoning
Hongyi Lin, Yang Liu, Jinhua Zhao +1
Foundation models are increasingly integrated into embodied intelligence systems, but directly assigning them structured prediction tasks requires precise geometric and numerical e…
Risk-Controllable Multi-View Diffusion for Driving Scenario Generation
Hongyi Lin, Wenxiu Shi, Heye Huang +5
Generating safety-critical driving scenarios is crucial for evaluating and improving autonomous driving systems, but long-tail risky situations are rarely observed in real-world da…