864 papers
TaPD is a unified, plug-and-play framework that employs temporal-adaptive progressive distillation and a temporal backfilling module to enable robust trajectory forecasting under variable and extremely short observation histories by transferring knowledge from long-horizon teachers and reconstructing missing past context.
NOVA introduces a novel 3D multi-object tracking framework that leverages large language models to reformulate tracking as an autoregressive next-step sequence completion task, enabling superior open-vocabulary generalization and identity consistency through spatio-temporal semantic modeling without relying on closed-set assumptions.
This paper proposes a two-stage human-robot collaboration framework that integrates satellite-derived indices for initial detection and USV-mounted SONAR for precise mapping to optimize targeted submerged aquatic vegetation harvesting in artificial lakes.
This paper introduces OccNL, the first benchmark for 3D semantic occupancy prediction under label noise, and proposes DPR-Occ, a novel framework that leverages dual-source partial label reasoning to achieve robust performance and prevent catastrophic collapse in noisy 3D voxel spaces where existing 2D noise-robust strategies fail.
The paper introduces SuperSuit, a bimodal interface that unifies robot-in-the-loop teleoperation and active demonstration for mobile manipulators through a shared isomorphic kinematic framework, enabling scalable, high-quality data acquisition and improved policy training without requiring downstream policy modifications.
This paper proposes a cost-effective, open-source platform utilizing 1:10 scaled mini-cars equipped with ROS2 and an ETSI-compliant OScar stack to bridge the gap between simulation and field testing for cooperative, connected, and automated vehicle research, demonstrated through a validated intersection collision warning application.
This paper presents a distributed control framework for cooperative manipulation that ensures safe consensus coordination through a hierarchical event-triggered Control Barrier Function architecture, validated by real-world experiments and simulations to achieve high precision with reduced computational and communication costs.
This paper demonstrates that while broad data diversity aids transfer across perceptual shifts like viewpoints, systematically aligning demonstrations across different robot morphologies through "data analogies" is far more effective for cross-embodiment transfer, yielding a 22.5% improvement in real-world success rates compared to unpaired datasets.
This paper proposes a training-free, plug-and-play spatio-temporal visual token pruning framework that significantly reduces computational latency for Vision-Language-Action based navigation while preserving high accuracy, as validated by both benchmark experiments and real-world deployment on a quadruped robot.
This paper introduces "control barrier corridors," a unified framework that converts control barrier functions into local safe goal regions to bridge the gap between functional safety filtering and geometric safe motion planning, enabling verifiably safe and persistent path following in complex, unknown environments.
This paper introduces a unified, smooth, low-dimensional design embedding that jointly optimizes shape, material distribution, and actuation for soft robots, demonstrating superior performance and efficiency over sequential strategies and existing parameterizations by structuring the design space to overcome computational challenges in nonlinear mechanics.
CFEAR-TR is a fast, lightweight, and robust radar-only localization pipeline that achieves state-of-the-art accuracy in adverse weather by jointly aligning live scans with both stored teach-phase maps and recent keyframes, narrowing the performance gap to LiDAR-based systems.
This paper introduces SG-DOR, a relational framework that utilizes a direction-aware graph neural network to infer scene graphs encoding physical attachments and direction-conditioned occlusion for robotic harvesting of pepper plants in dense canopies.
This paper presents a compact, underactuated monopedal robot that utilizes only three actuators and two reaction wheels to achieve multimodal locomotion—including rolling, targeted jumping, and self-righting—specifically designed for navigating diverse terrains on low-gravity extraterrestrial bodies.
This paper introduces a spatial calibration method for diffuse direct time-of-flight LiDARs that estimates per-pixel footprints and sensitivity maps in an RGB image plane using a scanned retroreflective patch, thereby enabling accurate cross-modal alignment and fusion despite the violation of standard single-ray assumptions.
This paper proposes a unified learning framework that integrates symbolic temporal reasoning with subsymbolic timing estimation from human demonstrations to generate executable, temporally parametrized plans for bimanual robot manipulation.
This paper presents a novel uncertainty-aware adaptive dynamics framework for underwater vehicle-manipulator systems that employs moving horizon estimation with convex physical constraints to achieve rapid, online parameter convergence and high-fidelity modeling, as validated by experiments on a BlueROV2 Heavy platform.
This paper introduces Fly360, a lightweight two-stage perception-decision pipeline that enables drones with panoramic views to achieve stable, omnidirectional obstacle avoidance by converting RGB observations into depth maps and employing a fixed random-yaw training strategy, outperforming traditional forward-view baselines in both simulation and real-world scenarios.
The paper proposes BEVLM, a framework that bridges the gap between spatially consistent Bird's-Eye View representations and Large Language Models by distilling semantic knowledge, thereby significantly enhancing both cross-view reasoning accuracy and safety-critical end-to-end driving performance.
This paper proposes a robust distributed UAV formation control technique that mitigates the adverse effects of relative pose measurement noise by decomposing and modifying gradient-descent commands based on estimated noise distributions, thereby significantly reducing oscillations and drift in real-world tight formations compared to standard methods.