695 papers
This paper presents the Interactive World Simulator, a fast and physically consistent framework leveraging consistency models to generate high-fidelity long-horizon video predictions that enable scalable robot policy training and reliable real-world evaluation using solely simulated data.
This paper presents a novel co-design approach that simultaneously optimizes the physical arrangement and control strategies of multiple rigidly connected quadcopters transporting a payload, utilizing a new H2-inspired robustness metric to maximize disturbance rejection capabilities, which is experimentally validated with diverse multi-UAV fleets and payload shapes.
This paper introduces vS-Graphs, a real-time Visual SLAM framework that tightly couples vision-based scene understanding with 3D scene graphs to generate semantically rich, hierarchical maps, achieving a 15.22% accuracy improvement over state-of-the-art methods while matching LiDAR-based semantic detection performance using only visual features.
This paper presents the design, fabrication, and experimental validation of a cost-effective, open-source, chain-driven mid-size quadruped robot featuring a sandwich-legged architecture and quasi-direct-drive actuators to achieve agile locomotion with improved reliability and safety.
This paper proposes a deterministic diffusion-based framework for controlling the probability density of nonlinear control-affine systems by leveraging a forward noise-excitation process and a reverse denoising feedback law to steer state distributions toward desired targets, with theoretical guarantees for drift-free and linear time-invariant dynamics.
The paper proposes SwitchMT, a novel methodology for scalable multi-task learning in resource-constrained autonomous agents that combines a Deep Spiking Q-Network with active dendrites and an adaptive task-switching policy to effectively mitigate task interference and outperform state-of-the-art methods in Atari games.
This paper introduces REI-Bench, the first benchmark for evaluating robot task planning under vague referring expressions, revealing that such vagueness significantly degrades performance and demonstrating that a task-oriented context cognition approach effectively mitigates this issue to improve accessibility for non-expert users.
This paper proposes SILVR, a self-improving framework that enables visual robotic planners to iteratively enhance their performance on novel tasks by continuously updating an in-domain video model using self-collected trajectories, achieving robust results without requiring ground-truth reward functions or expert demonstrations.
DAWN is a unified, end-to-end diffusion-based framework that bridges high-level intent and low-level robot actions through structured pixel motion representations, achieving state-of-the-art performance on benchmarks like CALVIN and MetaWorld while demonstrating robust real-world transfer with minimal finetuning.
Symskill is a unified framework that jointly learns symbolic abstractions and goal-oriented skills from unlabeled demonstrations to enable data-efficient, compositional, and real-time reactive long-horizon manipulation in dynamic environments.
CompassNav introduces a new navigation paradigm that shifts from path imitation to decision understanding by leveraging a novel dataset with geodesic distance annotations and a gap-aware hybrid reward function, enabling a 7B model to achieve state-of-the-art performance on both simulated benchmarks and physical robots.
This paper proposes a safety-guaranteed and optimal learning framework for autonomous systems that utilizes Weighted Signal Temporal Logic (WSTL) with structural pruning and log-transform techniques to efficiently solve preference-based learning problems as Mixed-Integer Linear Programs, validated through experiments in robotic navigation and Formula 1 racing.
MergeVLA is a merging-oriented Vision-Language-Action architecture that overcomes the non-mergeability of existing VLA experts by introducing task-masked sparse LoRA adapters and cross-attention-only action experts, enabling a single generalist agent to robustly handle diverse tasks and embodiments without performance degradation.
This paper introduces CostNav, the first physics-grounded navigation benchmark that evaluates autonomous agents using real-world economic data to reveal that current methods, despite varying in hardware and architecture, all fail to achieve economic viability due to negative contribution margins.
This paper introduces Partially Equivariant Reinforcement Learning, a framework that mitigates error propagation in symmetry-breaking environments by selectively applying group-invariant or standard Bellman backups based on local symmetry, thereby achieving superior sample efficiency and generalization compared to existing methods.
This paper presents a co-design framework that simultaneously optimizes robotic hand morphology and control policies to enable the end-to-end design, fabrication, and deployment of task-specific dexterous hands in under 24 hours.
This paper proposes C3, a novel uncertainty quantification method that trains controllable video models to generate high-resolution, calibrated confidence heatmaps at the subpatch level by estimating uncertainty in latent space and using strictly proper scoring rules, thereby enabling reliable hallucination detection and out-of-distribution identification for robotics applications.
This paper introduces PvP, a proprioceptive-privileged contrastive learning framework that enhances data efficiency and robustness in humanoid robot whole-body control by learning compact task-relevant representations without hand-crafted augmentations, supported by the new SRL4Humanoid evaluation framework.
This paper presents a reinforcement learning-based control framework that enables a lightweight, underactuated aerial manipulator with a differential 2-DoF arm to achieve precise six-DoF end-effector pose control and robust contact-rich manipulation through flight experiments.
This paper addresses the scarcity of labeled surgical robot data by introducing Cosmos-H-Surgical, a world model that generates realistic surgical videos and infers synthetic kinematics via an inverse dynamics model, enabling the training of superior surgical policies that outperform those trained solely on limited real-world demonstrations.