Related papers: Skill Transfer and Discovery for Sim-to-Real Learn…

Simulation-to-Real (Sim2Real) transfer learning, the machine learning technique that efficiently solves a real-world task by leveraging knowledge from computational data, has received increasing attention in materials science as a promising…

Learning effective visuomotor policies for robots purely from data is challenging, but also appealing since a learning-based system should not require manual tuning or calibration. In the case of a robot operating in a real environment the…

In recent years, the lack of successors for traditional skills has become an issue. To solve this problem, we propose a skill transfer system that presents tactile information in spatial tasks as a color map on an AR space. We believe that…

Reinforcement learning (RL) is widely used in autonomous driving tasks and training RL models typically involves in a multi-step process: pre-training RL models on simulators, uploading the pre-trained model to real-life robots, and…

Navigation and manipulation are core capabilities in Embodied AI, yet training agents with these capabilities in the real world faces high costs and time complexity. Therefore, sim-to-real transfer has emerged as a key approach, yet the…

Current reinforcement learning (RL) in robotics often experiences difficulty in generalizing to new downstream tasks due to the innate task-specific training paradigm. To alleviate it, unsupervised RL, a framework that pre-trains the agent…

We focus on the problem of teaching a robot to solve tasks presented sequentially, i.e., in a continual learning scenario. The robot should be able to solve all tasks it has encountered, without forgetting past tasks. We provide preliminary…

Behavior cloning has shown promise for robot manipulation, but real-world demonstrations are costly to acquire at scale. While simulated data offers a scalable alternative, particularly with advances in automated demonstration generation,…

In recent years, reinforcement learning (RL) has shown remarkable success in robotics when a fast and accurate simulator is available for a given task. When using RL and simulation, more simulator realism is generally beneficial but becomes…

We propose the first framework to learn control policies for vision-based human-to-robot handovers, a critical task for human-robot interaction. While research in Embodied AI has made significant progress in training robot agents in…

A popular paradigm in robotic learning is to train a policy from scratch for every new robot. This is not only inefficient but also often impractical for complex robots. In this work, we consider the problem of transferring a policy across…

We present a method for teaching dexterous manipulation tasks to robots from human hand motion demonstrations. Unlike existing approaches that solely rely on kinematics information without taking into account the plausibility of robot and…

Vision-based robotics often separates the control loop into one module for perception and a separate module for control. It is possible to train the whole system end-to-end (e.g. with deep RL), but doing it "from scratch" comes with a high…

Humanoid robots are envisioned as embodied intelligent agents capable of performing a wide range of human-level loco-manipulation tasks, particularly in scenarios requiring strenuous and repetitive labor. However, learning these skills is…

Enabling robots to learn long-horizon manipulation tasks from a handful of demonstrations remains a central challenge in robotics. Existing neuro-symbolic approaches often rely on hand-crafted symbolic abstractions, semantically labeled…

Unprecedented agility and dexterous manipulation have been demonstrated with controllers based on deep reinforcement learning (RL), with a significant impact on legged and humanoid robots. Modern tooling and simulation platforms, such as…

This paper develops a hierarchical learning and optimization framework that can learn and achieve well-coordinated multi-skill locomotion. The learned multi-skill policy can switch between skills automatically and naturally in tracking…

Autonomously trained agents that are supposed to play video games reasonably well rely either on fast simulation speeds or heavy parallelization across thousands of machines running concurrently. This work explores a third way that is…

Fine-tuning simulation-trained RL agents with real-world data often degrades crucial behaviors due to limited or skewed data distributions. We argue that designer priorities exist not just in reward functions, but also in simulation design…

This report presents the debates, posters, and discussions of the Sim2Real workshop held in conjunction with the 2020 edition of the "Robotics: Science and System" conference. Twelve leaders of the field took competing debate positions on…