864 papers
The paper introduces Contact-Grounded Policy (CGP), a dexterous visuotactile manipulation framework that leverages generative contact grounding to predict robot states and tactile feedback, converting them into executable targets for compliance control across both simulated and real-world tasks.
This paper introduces the NC-tALC dataset, a high-fidelity trajectory collection of 152 controlled experiments designed to characterize the interaction dynamics and decision-making of transitional autonomous vehicles during mandatory lane-changing maneuvers.
This paper proposes and evaluates an environment-aware path generation framework for robotic additive manufacturing that utilizes four distinct path planning algorithms to enable online structure design in dynamic, obstacle-rich environments, while establishing structural and computational metrics to identify the most effective planners for challenging construction scenarios.
This paper presents a privacy-preserving vision-language framework for medical interpreter robots that leverages locally deployed open-source LLMs and a novel annotated dataset to accurately detect clinical speech acts and generate human-like, appropriate robotic gestures.
Safe-Night VLA is a multimodal manipulation framework that enhances robot safety and robustness in unstructured environments by integrating long-wave infrared thermal perception into a vision-language-action backbone and enforcing deterministic safety constraints via control barrier functions.
EmboAlign is a data-free framework that enhances zero-shot robotic manipulation by leveraging vision-language models to extract compositional constraints, which are then used to select physically plausible video generation rollouts and refine robot trajectories, thereby significantly improving task success rates without requiring task-specific training data.
This paper proposes a two-stage framework combining constrained Bayesian Optimization-based Tree search (cBOT) for efficient single-robot trajectory generation and an STL-enhanced Kinodynamic Conflict-Based Search (STL-KCBS) for scalable multi-robot coordination, effectively addressing motion planning under Signal Temporal Logic specifications and kinodynamic constraints with demonstrated improvements in efficiency, safety, and real-world applicability.
This paper introduces TDGC, a hierarchical policy framework that bridges the gap between high-level navigation and low-level gait control for quadrupeds by using a task-level decision module to generate adaptable low-level targets, thereby improving robustness, sim-to-real transfer, and performance on mixed and out-of-distribution terrains.
The paper introduces CDF-Glove, a lightweight and low-cost ($230) cable-driven haptic feedback glove that enables high-quality dexterous teleoperation with 200 ms latency, significantly improving task success rates and the performance of imitation learning policies compared to traditional kinesthetic teaching.
This paper introduces HiLAM, a hierarchical latent action model that leverages a pretrained low-level extractor to aggregate short-term dynamic patterns into high-level latent skills, thereby enabling the discovery of temporally extended behaviors from actionless video data.
This paper presents OpenHEART, a robust and sample-efficient framework that enables legged manipulators to open diverse heterogeneous articulated objects by utilizing Sampling-based Abstracted Feature Extraction (SAFE) for compact geometric encoding and an Articulation Information Estimator (ArtIEst) for adaptive state estimation.
This paper presents the SILA Bot, a small-scale lizard-inspired robot that achieves effective locomotion on complex granular terrains by using proprioceptive signals to estimate substrate depth and a simple linear feedback controller to dynamically adapt its body movement patterns.
This paper proposes TraD-RL, a reinforcement learning framework for autonomous racing that integrates expert trajectory guidance, control barrier function-based safety constraints, and a multi-stage curriculum learning strategy to achieve stable training, safe operation, and performance surpassing expert levels in high-dynamic environments.
The paper presents DexEMG, a lightweight and cost-effective teleoperation system that utilizes a neural network to translate surface electromyography (sEMG) signals into dexterous hand poses, achieving high-precision control with strong generalization across diverse tasks without requiring intensive individual recalibration.
The paper proposes AnyCamVLA, a zero-shot framework that enhances the viewpoint robustness of pre-trained Vision-Language-Action models by virtually synthesizing test-time camera observations to match training configurations, thereby eliminating the need for fine-tuning, additional data, or architectural changes.
This paper presents a systematic evaluation demonstrating that while small synthetic novel view additions improve Video Place Recognition (VPR) performance, the effectiveness of larger additions depends more on the quantity of views and dataset imagery type than on the magnitude of the viewpoint change.
This paper proposes a simple, low-cost control strategy for small hopping robots that combines slope-adaptive touchdown angles and pre-takeoff corrective torque to effectively cancel destabilizing rotations and maintain stable hopping on inclined terrain.
This paper proposes a novel iterative convex MPC-DCBF framework that leverages supporting hyperplanes derived from exact polytope closest-point computations to enable fast, real-time, collision-free navigation for polytopic robots in complex environments without relying on geometric approximations.
FTSplat is a feed-forward framework that directly predicts continuous, simulation-ready triangle surfaces from multi-view images in a single pass, overcoming the optimization bottlenecks of NeRF and 3DGS while providing the explicit manifold geometry required for robotics and simulation.
The paper presents Swooper, a deep reinforcement learning framework that utilizes a two-stage training strategy to enable a lightweight quadrotor with a simple gripper to achieve high-speed aerial grasping at up to 1.5 m/s with an 84% success rate in real-world zero-shot deployment.