Related papers: PIRLNav: Pretraining with Imitation and RL Finetun…

Standard practice across domains from robotics to language is to first pretrain a policy on a large-scale demonstration dataset, and then finetune this policy, typically with reinforcement learning (RL), in order to improve performance on…

Recent advances in behavior cloning (BC) have enabled impressive visuomotor control policies. However, these approaches are limited by the quality of human demonstrations, the manual effort required for data collection, and the diminishing…

Imitation learning methods seek to learn from an expert either through behavioral cloning (BC) of the policy or inverse reinforcement learning (IRL) of the reward. Such methods enable agents to learn complex tasks from humans that are…

This work presents a case study of a learning-based approach for target driven map-less navigation. The underlying navigation model is an end-to-end neural network which is trained using a combination of expert demonstrations, imitation…

Preference-aligned robot navigation in human environments is typically achieved through learning-based approaches, utilizing user feedback or demonstrations for personalization. However, personal preferences are subject to change and might…

Object-Goal Navigation (ObjectNav) is a critical component toward deploying mobile robots in everyday, uncontrolled environments such as homes, schools, and workplaces. In this context, a robot must locate target objects in previously…

Guaranteeing constraint satisfaction is challenging in imitation learning (IL), particularly in tasks that require operating near a system's handling limits. Traditional IL methods, such as Behavior Cloning (BC), often struggle to enforce…

Reinforcement Learning (RL) has shown remarkable progress in simulation environments, yet its application to real-world robotic tasks remains limited due to challenges in exploration and generalization. To address these issues, we introduce…

Offline reinforcement learning (RL) algorithms can acquire effective policies by utilizing previously collected experience, without any online interaction. It is widely understood that offline RL is able to extract good policies even from…

Motion planning and control are crucial components of robotics applications like automated driving. Here, spatio-temporal hard constraints like system dynamics and safety boundaries (e.g., obstacles) restrict the robot's motions. Direct…

Imitation learning (IL) and reinforcement learning (RL) each offer distinct advantages for robotics policy learning: IL provides stable learning from demonstrations, and RL promotes generalization through exploration. While existing robot…

Learning robust driving policies from large-scale, real-world datasets is a central challenge in autonomous driving, as online data collection is often unsafe and impractical. While Behavioral Cloning (BC) offers a straightforward approach…

Behavior cloning (BC) is often practical for robot learning because it allows a policy to be trained offline without rewards, by supervised learning on expert demonstrations. However, BC does not effectively leverage what we will refer to…

Designing rewards for Reinforcement Learning (RL) is challenging because it needs to convey the desired task, be efficient to optimize, and be easy to compute. The latter is particularly problematic when applying RL to robotics, where…

Humanoid robots have the potential to mimic human motions with high visual fidelity, yet translating these motions into practical, physical execution remains a significant challenge. Existing techniques in the graphics community often…

We present a large-scale study of imitating human demonstrations on tasks that require a virtual robot to search for objects in new environments -- (1) ObjectGoal Navigation (e.g. 'find & go to a chair') and (2) Pick&Place (e.g. 'find mug,…

Imitation learning is an effective tool for robotic learning tasks where specifying a reinforcement learning (RL) reward is not feasible or where the exploration problem is particularly difficult. Imitation, typically behavior cloning or…

Reinforcement learning (RL)-based motion imitation methods trained on demonstration data can effectively learn natural and expressive motions with minimal reward engineering but often struggle to generalize to novel environments. We address…

Scaling Reinforcement Learning to in-the-wild social robot navigation is both data-intensive and unsafe, since policies must learn through direct interaction and inevitably encounter collisions. Offline Imitation learning (IL) avoids these…

Object goal navigation (ObjectNav) is a fundamental task in embodied AI, requiring an agent to locate a target object in previously unseen environments. This task is particularly challenging because it requires both perceptual and cognitive…