Related papers: To the Noise and Back: Diffusion for Shared Autono…

A long-standing goal in AI is to develop agents capable of solving diverse tasks across a range of environments, including those never seen during training. Two dominant paradigms address this challenge: (i) reinforcement learning (RL),…

Developing robust autonomous loco-manipulation skills for humanoids remains an open problem in robotics. While RL has been applied successfully to legged locomotion, applying it to complex, interaction-rich manipulation tasks is harder…

Autonomous navigation and exploration in unmapped environments remains a significant challenge in robotics due to the difficulty robots face in making commonsense inference of unobserved geometries. Recent advancements have demonstrated…

Generative models such as diffusion models, excel at capturing high-dimensional distributions with diverse input modalities, e.g. robot trajectories, but are less effective at multi-step constraint reasoning. Task and Motion Planning (TAMP)…

The validation of autonomous driving systems benefits greatly from the ability to generate scenarios that are both realistic and precisely controllable. Conventional approaches, such as real-world test drives, are not only expensive but…

In many real-world settings, agents must learn from an offline dataset gathered by some prior behavior policy. Such a setting naturally leads to distribution shift between the behavior policy and the target policy being trained - requiring…

This paper addresses the problem of generating dynamically admissible trajectories for control tasks using diffusion models, particularly in scenarios where the environment is complex and system dynamics are crucial for practical…

Fine-tuning diffusion policies with reinforcement learning (RL) presents significant challenges. The long denoising sequence for each action prediction impedes effective reward propagation. Moreover, standard RL methods require millions of…

Shared autonomy requires principled mechanisms for allocating and transferring control between a human and an autonomous agent. Existing approaches often rely on blending control inputs between human and autonomous agent or switching rules,…

We present a computational framework for synthesis of distributed control strategies for a heterogeneous team of robots in a partially observable environment. The goal is to cooperatively satisfy specifications given as Truncated Linear…

Empowering embodied agents, such as robots, with Artificial Intelligence (AI) has become increasingly important in recent years. A major challenge is task open-endedness. In practice, robots often need to perform tasks with novel goals that…

In the field of Human-Robot Interaction (HRI), many researchers study shared control systems. Shared control is when a person and agent both contribute to the performance of a task in a collaborative way, often by providing control inputs…

Evaluating the performance of autonomous vehicle planning algorithms necessitates simulating long-tail safety-critical traffic scenarios. However, traditional methods for generating such scenarios often fall short in terms of…

We present a shared control paradigm that improves a user's ability to operate complex, dynamic systems in potentially dangerous environments without a priori knowledge of the user's objective. In this paradigm, the role of the autonomous…

Multitask learning poses significant challenges due to the highly multimodal and diverse nature of robot action distributions. However, effectively fitting policies to these complex task distributions is often difficult, and existing…

Bridging the gap between diffusion models and human preferences is crucial for their integration into practical generative workflows. While optimizing downstream reward models has emerged as a promising alignment strategy, concerns arise…

Opening heavy, self closing doors, especially those that require pulling remains a long standing challenge in robotics. Humans naturally employ both arms in a dexterous manner, rotating the handle, widening the gap, holding the door,…

Although deep reinforcement learning (DRL) has shown promising results for autonomous navigation in interactive traffic scenarios, existing work typically adopts a fixed behavior policy to control social vehicles in the training…

In this paper, we propose a novel approach called DIffusion-guided DIversity (DIDI) for offline behavioral generation. The goal of DIDI is to learn a diverse set of skills from a mixture of label-free offline data. We achieve this by…

When performing tasks like laundry, humans naturally coordinate both hands to manipulate objects and anticipate how their actions will change the state of the clothes. However, achieving such coordination in robotics remains challenging due…