Related papers: AVO: Amortized Value Optimization for Contact Mode…

The paper addresses the problem of providing suitable reference trajectories in motion planning problems for autonomous vehicles. Among the various approaches to compute a reference trajectory, our aim is to find those trajectories which…

Reinforcement Learning has become a standard paradigm for aligning Large Language Models with human intent and task requirements. While Group Relative Policy Optimization offers an efficient, value-model-free alternative to Proximal Policy…

Robotic manipulation of deformable objects remains a challenging task. One such task is folding a garment autonomously. Given start and end folding positions, what is an optimal trajectory to move the robotic arm to fold a garment? Certain…

Robotic manipulation in complex scenes demands precise perception of task-relevant details, yet fixed or suboptimal viewpoints often impair fine-grained perception and induce occlusions, constraining imitation-learned policies. We present…

Agentic Variation Operators (AVO) are a new family of evolutionary variation operators that replace the fixed mutation, crossover, and hand-designed heuristics of classical evolutionary search with autonomous coding agents. Rather than…

PointGoal navigation in indoor environment is a fundamental task for personal robots to navigate to a specified point. Recent studies solved this PointGoal navigation task with near-perfect success rate in photo-realistically simulated…

This letter aims to maximize the average throughput via the joint design of the transmit power and trajectory for unmanned aerial vehicle (UAV)-enabled network. The conventional way to tackle this problem is based on the alternating…

Autonomous vehicles (AVs) have the potential to prevent accidents caused by drivers errors and reduce road traffic risks. Due to the nature of heavy vehicles, whose collisions cause more serious crashes, the weights of vehicles need to be…

We study how to improve large foundation vision-language-action (VLA) systems through online reinforcement learning (RL) in real-world settings. Central to this process is the value function, which provides learning signals to guide VLA…

Dexterous manipulation is a cornerstone capability for robotic systems aiming to interact with the physical world in a human-like manner. Although vision-based methods have advanced rapidly, tactile sensing remains crucial for fine-grained…

Autonomous driving has attracted great interest due to its potential capability in full-unsupervised driving. Model-based and learning-based methods are widely used in autonomous driving. Model-based methods rely on pre-defined models of…

Learning-based visual odometry (VO) algorithms achieve remarkable performance on common static scenes, benefiting from high-capacity models and massive annotated data, but tend to fail in dynamic, populated environments. Semantic…

The technology for Visual Odometry (VO) that estimates the position and orientation of the moving object through analyzing the image sequences captured by on-board cameras, has been well investigated with the rising interest in autonomous…

Human hand actions are quite complex, especially when they involve object manipulation, mainly due to the high dimensionality of the hand and the vast action space that entails. Imitating those actions with dexterous hand models involves…

In this work, we aim to learn a unified vision-based policy for multi-fingered robot hands to manipulate a variety of objects in diverse poses. Though prior work has shown benefits of using human videos for policy learning, performance…

In this paper, we address the problem of task-oriented grasping for humanoid robots, emphasizing the need to align with human social norms and task-specific objectives. Existing methods, employ a variety of open-loop and closed-loop…

Manipulating deformable objects arises in daily life and numerous applications. Despite phenomenal advances in industrial robotics, manipulation of deformable objects remains mostly a manual task. This is because of the high number of…

Real-world cooperation often requires intensive coordination among agents simultaneously. This task has been extensively studied within the framework of cooperative multi-agent reinforcement learning (MARL), and value decomposition methods…

Teleoperation provides a way for human operators to guide robots in situations where full autonomy is challenging or where direct human intervention is required. It can also be an important tool to teach robots in order to achieve…

We propose a novel deep visual odometry (VO) method that considers global information by selecting memory and refining poses. Existing learning-based methods take the VO task as a pure tracking problem via recovering camera poses from image…