864 papers
EmboTeam is a novel framework that enhances embodied multi-robot collaboration by cascading LLM-based instruction parsing into formal PDDL planning and reactive behavior tree execution, achieving significantly higher task success rates on the new MACE-THOR benchmark compared to existing baselines.
The paper presents MOSAIC, a scalable autonomy framework that enables a single operator to supervise heterogeneous robotic teams for scientific exploration in hostile environments by dynamically allocating tasks based on Points of Interest, as demonstrated by a successful lunar prospecting field experiment where the team maintained high task completion and autonomy levels despite a robot failure.
DDP-WM is a novel, efficient world model that addresses the computational bottlenecks of dense Transformer-based approaches by employing Disentangled Dynamics Prediction to separate sparse primary physical interactions from secondary background updates, thereby achieving significant inference speedups and improved planning success rates across diverse robotic tasks.
This paper introduces the Exploratory and Focused Manipulation (EFM) problem to address visual occlusion in robot manipulation, proposing the EFM-10 benchmark and a Bimanual Active Perception (BAP) strategy that effectively leverages dual-arm coordination for active vision and force sensing.
The paper proposes MAE-Select, a novel framework that leverages pre-trained multi-view masked autoencoder representations to dynamically optimize viewpoints for single-camera robotic manipulation, enabling the system to surpass the performance of static multi-camera setups by actively selecting the most informative views without requiring labeled data.
This paper proposes an infinite-dimensional closed-loop inverse kinematics framework for underactuated soft robots that leverages differentiable neural operators to learn actuation-to-shape mappings, enabling efficient task-space control by reasoning about the robot's entire continuous shape rather than finite configurations.
This paper presents a scout-rover cooperation framework that utilizes a legged robot's proprioceptive terrain sensing to generate online strength maps, enabling a wheeled rover to estimate traversal risks and safely navigate hazardous, deformable planetary terrains.
This paper presents LACE, a learning-based framework that leverages deep neural networks with attention mechanisms and contraction-based stability guarantees to model smooth, environment-aware GNSS covariance dynamics, thereby enhancing state estimation accuracy and control safety for high-speed autonomous racing in challenging conditions.
This paper proposes an interpretable, multimodal gesture recognition framework that fuses inertial and capacitive sensor data via log-likelihood ratio to enable robust, real-time, hands-free teleoperation of drones and mobile robots, supported by a new dataset and demonstrating performance comparable to vision-based methods with significantly lower computational costs.
This paper proposes a reinforcement learning-based approach for coverage path planning on 3D surfaces using deformable objects, which leverages harmonic UV mapping and scaled grouped convolutions to process contact feedback in simulation and successfully demonstrates effective wiping tasks on a physical Kinova Gen3 manipulator.
This paper presents a data-driven framework that combines Koopman operator theory with the Safe Set Algorithm to enable real-time, whole-body safe control of nonlinear robotic systems by formulating tracking and safety constraints within a single quadratic program.
This paper proposes a Dual-Interaction-Aware Cooperative Control (DIACC) strategy based on Multi-Agent Reinforcement Learning, which integrates decentralized decision-making, centralized value estimation, and a novel reward design to effectively alleviate mixed traffic congestion by distinguishing between cooperative and observational vehicle interactions.
This paper introduces GAIDE, a neural informed sampler that leverages graph-based attention masking to encode spatial and embodiment structures, thereby significantly improving the efficiency and success rate of sampling-based motion planning for robotic manipulators compared to existing methods.
This paper introduces Act-Observe-Rewrite (AOR), a framework enabling multimodal language models to iteratively improve robot manipulation policies by synthesizing and rewriting executable Python controller code based on visual feedback and failure analysis, achieving high success rates across tasks without demonstrations, reward engineering, or gradient updates.
This paper presents a fully autonomous navigation stack for a quadruped robot running on low-power edge hardware without GPUs or network connectivity, which successfully navigated complex underground mine environments with a 100% success rate across 20 trials using a combination of LiDAR-inertial odometry, map-based localization, and classical planning algorithms.
PTLD introduces a sim-to-real framework for dexterous manipulation that distills privileged real-world tactile data into a robust state estimator, enabling proprioceptive policies trained in simulation to significantly improve performance on complex in-hand tasks without requiring realistic tactile simulation.
The paper proposes Many-RRT*, a robust sampling-based motion planner that simultaneously grows trees from multiple inverse kinematics solutions to overcome the challenges of non-invertible forward kinematics in high-degree-of-freedom serial manipulators, thereby achieving significantly higher success rates and lower trajectory costs compared to traditional RRT methods.
The paper introduces MEMO, a neuro-symbolic framework that aggregates and synthesizes multi-user natural language corrections and task successes into a retrieval-augmented skillbook, enabling robots to dynamically generate generalized skills and improve performance on novel manipulation tasks.
This paper presents a distributed and decentralized vision-based state estimation framework using a Distributed Decentralized Extended Information Filter (DDEIF) to enable robust, GPS-denied cooperative slung load transportation by multiple UAVs, demonstrating its effectiveness and resilience to sensor and communication losses through Gazebo simulations.
This paper introduces a novel framework that combines Distributional Reinforcement Learning with Imitation Learning to train mobile manipulators to execute risk-aware, reactive whole-body motions in dynamic, unmapped environments by leveraging egocentric depth observations and runtime-adjustable risk sensitivity.