A deployment-oriented instance segmentation framework for resource-constrained lunar robotics that jointly addresses calibration and system-level fault exposure under strict compute constraints is presented and an integrated approach and a blueprint for a reliable and safe AI perception framework under space deployment...
Siddhant Shete, Hilmi Doğu Küçüker, Udo Frese et al.· 0 citations
Across diverse goal-reaching tasks, DCRL substantially outperforms prior flat offline GCRL methods, and on the five most challenging long-horizon OGBench tasks, it improves the best prior average score from 55 to 64, surpassing all flat and hierarchical baselines.
While diffusion models effectively capture multimodal behavioral priors for autonomous driving, offline reinforcement learning (RL) policies remain susceptible to distribution shift, heavy-tailed risk signals, out-of-distribution (OOD) action generation, and high-dimensional state redundancy. To address these challenge...
Qisong Guo, Jingtang Chen, Zhilin Chen et al.· 0 citations
FineVLA, an open framework for action-aligned fine-grained VLA supervision, is introduced and the largest real-world gains appear on pose, color, and approach direction, and approach direction--factors where goal-level instructions provide no guidance.
FlatLands provides a rigorous testbed for uncertainty-aware indoor mapping and generative completion for embodied navigation and is instantiate the task as an end-to-end monocular RGB-to-floormaps pipeline.
Subhransu S. Bhattacharjee, Dylan Campbell, Rahul Shome· arXiv.org· 0 citations
This paper presents an information-gain-guided reinforcement-learning sensor-selection framework for single-vessel tracking in heterogeneous maritime sensor networks. The proposed approach is motivated by information-theoretic sensor management: instead of activating all sensors or repeatedly performing computationally...
Andrei Starodubov, Yaqub Aris Prabowo, Andreas Hadjipieris et al.· 0 citations
This work characterize models from this family of methods as JEPA-WMs and investigates the technical choices that make algorithms from this class work, and proposes a model that outperforms two established baselines, DINO-WM and V-JEPA-2-AC, in both navigation and manipulation tasks.
Basile Terver, Tsung-Yen Yang, Jean Ponce et al.· Trans. Mach. Learn. Res.· 49 citations· ⚡7
TRACE (Transparent Reasoning Architecture for Credible Execution), a decision framework that ensures every autonomous action can be traced back to sensor evidence through documented causal chains, is presented.
This paper proposes CrashDiffuser, a closed-loop VLM-guided diffusion framework that decouples semantic collision reasoning from continuous trajectory synthesis through a hierarchical collision-intent interface derived from the requested target contact region.
Shucheng Zhang, Yuang Zhang, Bingzhang Wang et al.· 0 citations
DiffuSearch is introduced, a novel hybrid planner that uses a unified set of objectives across generation and refinement, and achieves strong and often state-of-the-art performance, substantially reducing collisions and improving comfort, particularly in complex, interactive scenarios.
Steffen Hagedorn, Aron Distelzweig, Alexandru Condurache· 1 citation
This work asks whether explicitly modeling change (a per-object change gate plus a residual delta head that perturbs only the objects the gate flags) is a more effective and interpretable bias for physical prediction and control.
For embodied systems, predictive agreement alone does not determine whether evidence warrants action; evidential origin matters. Repeated inference over one observation can multiply agreement without adding evidence, while source-local values do not reveal whether outputs have separately countable origins. PACT treats...
Zekai Jin, Hanrong Zhang, Yihong Tang et al.· 0 citations
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.
Gemini Robotics ER 2 helps robots reason, collaborate, and solve real-world tasks. It represents a step change in video understanding, tool orchestration, and multi-robot collaboration for robotic applications.
From feet to fingertips — we are teaching robots intelligent whole-body control, fine dexterity, and teamwork to complete a broad range of complex tasks.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
