Related papers: MuJoCo Playground
We tackle the recently introduced benchmark for whole-body humanoid control HumanoidBench using MuJoCo MPC. We find that sparse reward functions of HumanoidBench yield undesirable and unrealistic behaviors when optimized; therefore, we…
Embodied AI research is undergoing a shift toward vision-centric perceptual paradigms. While massively parallel simulators have catalyzed breakthroughs in proprioception-based locomotion, their potential remains largely untapped for…
We present IndoorSim-to-OutdoorReal (I2O), an end-to-end learned visual navigation approach, trained solely in simulated short-range indoor environments, and demonstrates zero-shot sim-to-real transfer to the outdoors for long-range…
Minecraft's complexity and diversity as an open world make it a perfect environment to test if agents can learn, adapt, and tackle a variety of unscripted tasks. However, the development and validation of novel agents in this setting…
This paper presents ArticuBot, in which a single learned policy enables a robotics system to open diverse categories of unseen articulated objects in the real world. This task has long been challenging for robotics due to the large…
We present pyCub, an open-source physics-based simulation of the humanoid robot iCub, along with exercises to teach students the basics of humanoid robotics. Compared to existing iCub simulators (iCub SIM, iCub Gazebo), which require C++…
Teaching a multi-fingered dexterous robot to grasp objects in the real world has been a challenging problem due to its high dimensional state and action space. We propose a robot-learning system that can take a small number of human…
The present study introduces an Android based application that focuses on promoting students' learning experience when interacting with Lego Mindstorms Robotic Kit NXT. A thorough investigation of the current literature reveals that there…
Action-conditioned video prediction models (often referred to as world models) have shown strong potential for robotics applications, but existing approaches are often slow and struggle to capture physically consistent interactions over…
Robots are a popular platform for introducing computing and artificial intelligence to novice programmers. However, programming state-of-the-art robots is very challenging, and requires knowledge of concurrency, operation safety, and…
Riichi Mahjong is a multi-player, imperfect-information game characterized by stochasticity and high-dimensional state spaces. These attributes present a unique combination of challenges that mirror complex real-world decision-making…
Inspired by the diversity and depth of XLand and the simplicity and minimalism of MiniGrid, we present XLand-MiniGrid, a suite of tools and grid-world environments for meta-reinforcement learning research. Written in JAX, XLand-MiniGrid is…
Robots are often built from standardized assemblies, (e.g. arms, legs, or fingers), but each robot must be trained from scratch to control all the actuators of all the parts together. In this paper we demonstrate a new approach that takes a…
We present Human to Humanoid (H2O), a reinforcement learning (RL) based framework that enables real-time whole-body teleoperation of a full-sized humanoid robot with only an RGB camera. To create a large-scale retargeted motion dataset of…
A universal controller for any robot morphology would greatly improve computational and data efficiency. By utilizing contextual information about the properties of individual robots and exploiting their modular structure in the…
We present a feasibility-seeking approach to neural network training. This mathematical optimization framework is distinct from conventional gradient-based loss minimization and uses projection operators and iterative projection algorithms.…
This work presents a meta-reinforcement learning approach to develop a universal locomotion control policy capable of zero-shot generalization across diverse quadrupedal platforms. The proposed method trains an RL agent equipped with a…
Sim2real, that is, the transfer of learned control policies from simulation to real world, is an area of growing interest in robotics due to its potential to efficiently handle complex tasks. The sim2real approach faces challenges due to…
Learning policies in simulation is promising for reducing human effort when training robot controllers. This is especially true for soft robots that are more adaptive and safe but also more difficult to accurately model and control. The…
Autonomous Underwater Vehicles (AUVs) require reliable six-degree-of-freedom (6-DOF) position control to operate effectively in complex and dynamic marine environments. Traditional controllers are effective under nominal conditions but…