A modular, high-fidelity simulation framework for the development and benchmarking of flight control strategies in fixed-wing aerial robots operating near the ground that models full 6DoF rigid-body physics, semi-empirical ground-effect aerodynamics, actuator dynamics, sensor noise, and environmental disturbances.
Matteo El Hariry, Pedro U. Lima, Andrej Orsula et al.· 0 citations
SimpleMemVLA, a VLA without a dedicated memory module that uses the backbone's native video context directly as memory, achieves state-of-the-art results on four memory benchmarks without loss on general-purpose control, and with the same backbone and training setup it outperforms retrieval, compression and recurrent-s...
C. Yin, Wang Xu, Jun-Peng Yang et al.· 4 citations
This paper proposes a transferable Map of Dynamics (MoD) framework that generalizes to unknown environments using only egocentric 3D LiDAR point clouds to overcome the long-standing limitation of traditional MoD methods. While MoDs are essential for encoding human motion characteristics to enable accurate pedestrian tr...
Azusa Sawada, Allan Wang, Hideo Saito et al.· 0 citations
It is suggested that variation among actions sampled by a generative policy can serve as an online control signal for balancing assistance and compliance in physical human-robot interaction.
Aoi Otake, Ferdinand Hartmann, Ko Igari et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Multi-fingered robots promise the speed and dexterity of human hands, yet challenging problems such as precise assembly have remained out of reach. These tasks are contact-rich, making data collection for imitation learning difficult, and sparse-reward, making direct exploration with reinforcement learning (RL) intract...
Tyler Ga Wei Lum, Kushal Kedia, C. Karen Liu et al.· 0 citations
Hierarchical vision-language-action (Hi-VLA) systems have emerged as a promising paradigm for complex robot manipulation, by using high-level VLM planners to decompose tasks into language subgoals executed by low-level VLA controllers. Despite recent empirical progress, there is a lack of unified design principles for...
Jiaheng Hu, Mohit Shridhar, Caden Lu et al.· 0 citations
The Torque Adaptation Module (TAM), a learned module that adapts the torque commands sent to the robot to match the behavior of an ideal robot, is introduced and shows that TAM improves zero-shot real-robot execution compared to online system identification and RMA baselines and enables robust dynamic manipulation perf...
Dongwon Son, Florian Shkurti, Jason Lee et al.· arXiv.org· 0 citations
HeteroGenManip is proposed, a task-conditioned, two-stage framework designed to decouple initial grasp from complex interaction execution, and achieves robust intra-category shape and pose generalization.
This work proposes AtomicVLA, a unified planning-and-execution framework that jointly generates task-level plans, atomic skill abstractions, and fine-grained actions, and introduces a flexible routing encoder that automatically assigns dedicated atomic experts to new skills, enabling continual learning.
Likui Zhang, Tao Tang, Zhihao Zhan et al.· arXiv.org· 19 citations· ⚡3
A deep AIF framework that integrates a diffusion policy as the policy model and a multiple timescale recurrent state-space model (MTRSSM) as the world model is proposed, demonstrating how AIF based on EFE minimization can unify exploration and goal-directed navigation in real-world robotic settings.
Riko Yokozawa, Kentaro Fujii, Yuta Nomura et al.· arXiv.org· 1 citation
Q-SVMPC is proposed, a Q-guided Stein variational MPC method with an RL-informed policy prior, which casts learning-based MPC as trajectory-level posterior inference and refines trajectory particles via SVGD under learned soft Q-value guidance to explicitly preserve diverse solutions.
Shizhe Cai, Zeya Yin, Jayadeep Jacob et al.· 3 citations
This work introduces TANGO, the first whole-body vision-language navigation framework for language-conditioned humanoid traversal in cluttered environments, and demonstrates state-of-the-art performance in vision-language navigation, while outperforming strong modular baselines in navigating challenging scenes requirin...
A. Li, Yu-Xin Chen, Zhao-Bo Li et al.· 4 citations
A new system identifies and corrects unreliable object descriptions stored in a robot’s memory, improving the robot’s ability to interact with its environment.
Robots are getting smarter, but how can their hardware match that growth? New Microsoft Research findings show that moving AI inference beyond the robot can improve task success, boost efficiency, and support more advanced physical AI workloads. The post Offloaded inference for real-world physical AI robotics appeared first on Microsoft Research.
