相关论文: Hyper-Universal Policy Approximation: Learning to …

The control of a robot for manipulation tasks generally relies on object detection and pose estimation. An attractive alternative is to learn control policies directly from raw input data. However, this approach is time-consuming and…

This paper addresses the challenge of navigation in large, visually complex environments with sparse rewards. We propose a method that uses object-oriented macro actions grounded in a topological map, allowing a simple Deep Q-Network (DQN)…

Online policy learning directly in the physical world is a promising yet challenging direction for embodied intelligence. Unlike simulation, real-world systems cannot be arbitrarily accelerated, cheaply reset, or massively replicated, which…

Universal Adversarial Perturbations (UAPs) are a prominent class of adversarial examples that exploit the systemic vulnerabilities and enable physically realizable and robust attacks against Deep Neural Networks (DNNs). UAPs generalize…

Recent advances in world models have shown promise for modeling future dynamics of environmental states, enabling agents to reason and act without accessing real environments. Current methods mainly perform single-step or fixed-horizon…

Robot learning approaches such as behavior cloning and reinforcement learning have shown great promise in synthesizing robot skills from human demonstrations in specific environments. However, these approaches often require task-specific…

A generalist robot equipped with learned skills must be able to perform many tasks in many different environments. However, zero-shot generalization to new settings is not always possible. When the robot encounters a new environment or…

When deployed, AI agents will encounter problems that are beyond their autonomous problem-solving capabilities. Leveraging human assistance can help agents overcome their inherent limitations and robustly cope with unfamiliar situations. We…

Video prediction models combined with planning algorithms have shown promise in enabling robots to learn to perform many vision-based tasks through only self-supervision, reaching novel goals in cluttered scenes with unseen objects.…

Human learning and intelligence work differently from the supervised pattern recognition approach adopted in most deep learning architectures. Humans seem to learn rich representations by exploration and imitation, build causal models of…

Conventional reinforcement learning (RL) methods can successfully solve a wide range of sequential decision problems. However, learning policies that can generalize predictably across multiple tasks in a setting with non-Markovian reward…

Modern cyber-physical systems are becoming increasingly complex to model, thus motivating data-driven techniques such as reinforcement learning (RL) to find appropriate control agents. However, most systems are subject to hard constraints…

Goal-conditioned policy learning for robotic manipulation presents significant challenges in maintaining performance across diverse objectives and environments. We introduce Hyper-GoalNet, a framework that generates task-specific policy…

How can we design neural networks that allow for stable universal approximation of maps between topologically interesting manifolds? The answer is with a coordinate projection. Neural networks based on topological data analysis (TDA) use…

Reasoning about object affordances allows an autonomous agent to perform generalised manipulation tasks among object instances. While current approaches to grasp affordance estimation are effective, they are limited to a single hypothesis.…

Building deep reinforcement learning agents that can generalize and adapt to unseen environments remains a fundamental challenge for AI. This paper describes progresses on this challenge in the context of man-made environments, which are…

Unsupervised Environment Design (UED) has emerged as a promising approach to developing general-purpose agents through automated curriculum generation. Popular UED methods focus on Open-Endedness, where teacher algorithms rely on stochastic…

Policy steering is an emerging way to adapt robot behaviors at deployment-time: a learned verifier analyzes low-level action samples proposed by a pre-trained policy (e.g., diffusion policy) and selects only those aligned with the task.…

Building generalist robot policies that can handle diverse tasks in open-ended environments is a central challenge in robotics. To leverage knowledge from large-scale pretraining, prior work (VLA) has typically built generalist policies…

The ultimate navigation efficiency of mobile robots in human environments will depend on how we will appraise them: merely as impersonal machines or as human-like agents. In the latter case, an agent may take advantage of the cooperative…