LeHome: A New Simulation Environment for Deformable Object Manipulation in Home Scenarios
A research team has released LeHome, a simulation environment specifically designed for deformable object manipulation t…
📂 Research
Latest articles in Research
New Method Enables Provably Safe Constraint Satisfaction for Black-Box Hybrid Dynamical Systems
A latest paper on arXiv proposes a control policy learning method for black-box hybrid dynamical systems that rigorously…
No More Clumsy Robot Handovers: Adaptive Framework Makes Human-Robot Collaboration More Natural
A new study proposes an adaptive robot handover framework that dynamically adjusts object delivery orientation and angle…
Learning-Augmented Robotic Automation Moves onto Real Production Lines
A latest arXiv paper explores bringing learning-based robotic control from the lab to real manufacturing production line…
New Study Reveals How Palm Degrees of Freedom Enhance Thumb Opposability in Robotic Hands
A latest arXiv paper systematically investigates how palm degrees of freedom enhance thumb opposability in five-fingered…
New Closed-Loop Autonomous Learning Framework for Robots Powered by LLMs
Researchers have proposed a closed-loop autonomous learning framework driven by large language models that enables robot…
V-STC: A New Breakthrough in Multi-Vehicle Cooperative Trajectory Planning
Researchers propose the Variable-Time-Step Spatio-Temporal Corridor (V-STC) method, which significantly improves the tim…
New Research Tackles the Localization Challenge for Highway Autonomous Driving
A latest paper on arXiv proposes a robust localization system designed specifically for highway scenarios, addressing ke…
New Framework Significantly Boosts Energy Efficiency in Multi-Robot Coverage Path Planning
A latest arXiv paper proposes an energy-efficient multi-robot coverage path planning framework for non-convex regions, o…
dWorldEval: Discrete Diffusion World Models Enable Large-Scale Robot Policy Evaluation
Researchers propose the dWorldEval framework, leveraging discrete diffusion world models as scalable evaluation proxies.…
SNGR Framework: Precisely Fixing Non-Gaussian Traps in SLAM
Researchers propose the Selective Non-Gaussian Refinement (SNGR) framework, which introduces a nested sampling mechanism…
"Wiggle Then Throw": A New Zero-Shot Approach to Dynamic Rope Manipulation
A research team has proposed a novel method for zero-shot dynamic rope manipulation using learned simulation priors. By …