研究资料库

From Language Models to World-Acting Systems: Progress and Limits of Agentic AI across Digital, Social, Virtual, and Physical Environments

Development of a Humanoid Robot Prototype for Multimodal Human-Robot Interaction

LIBERO-RECOVER: Beyond Task Success Towards Failure Recovery in Robotic Manipulation Models

Morphology and actuation as inductive biases in robotic hand manipulation

Temporal Tactile Encoding and Compliance for Intent-Aware Robot-to-Human Bimanual Handover

Open-Set 3D Scene Graphs for Field Robotics: An Outdoor Case Study

Human-Human & Human-Robot Interaction Transformer (H2INT) for Robot Navigation in Dense and Uncertain Crowds

Dressing in Motion: A Human Motion-Aware Diffusion Policy for Robot-Assisted Dressing

Coupled Control and Wireless World Models for Resilient Remote Robotic Control

RoboSPA: Can VLA Models Go Beyond Simple Scenes and Short-Horizon Tasks?

Reasoning Without Inference Cost: Latent Semantic Scaffolding for Robot VLA Policies

FIRE-LIVWO: Robust LiDAR-Inertial-Visual-Wheel Odometry via Failure-Immune mmWave Radar Enhancement

MINT: A Unified Model for World-Space Camera and Hand Motion Estimation from Scalable Egocentric Pipeline Supervision

Towards Neuro-Symbolic Procedural Reasoning for Long-Horizon Vision-Language-Action Manipulation

One Word, Different Action: A Real-Robot Benchmark for Language-Conditioned Embodied Reasoning

APEX-RBD: Mixed-Precision Exploration Framework for Hardware-Efficient Robot Dynamics Accelerator Design

TacPAC: Tactile Prediction and Real-Time Action Correction in World-Action Models for Contact-Rich Manipulation

Same Trajectory, Contradictory Rewards (ROBORMBENCH): Paraphrase Fragility in Vision Language Reward Models

A Schema Bounded Language Model for Refining Robot Policies Without Destabilizing Local Learning

What Matters, When? Diagnosing and Improving Conditional Visual Grounding in Visuomotor Imitation Policies

NavArena: Automated Construction of Goal-Oriented Navigation Benchmarks from 3D Gaussian Splatting Reconstructions

IRWOZ 2.0: A Large Language Model-driven Dialogue Dataset for Industrial Robot Conversations

Rethinking 3D Noise: Learning 3D-Aware Video Priors via Optimization-Free Morphological Perturbations

Building Pretraining Data for World Models: An Unreal Engine-Based Pipeline for Action-Conditioned Video Generation

Toward Unified Robot Learning: Bridging Representation, Vision-Language-Action, and World Models

MulDP: Multimodal Diffusion Policy for Autonomous Quadruped Parkour Navigation across Complex Terrains

R2S-Eval: Robot Evaluation with Real-to-Sim Calibration via Vision-Language Models

Adaptive Vision-Language Grasping via Composable Foundation Priors and Generalizable Grasp Synthesis

FailBench: How Reliable are VLMs at Judging Robot Task Success?

FWBC-VLA: Force-Aware Whole-Body Compensation for Contact-Rich Loco-Manipulation