arXiv subjects

Jean Chagas Vaz

Publications and source records attributed to Jean Chagas Vaz.

5 recordsLinked to original sources

arXiv2026

Towards Miniature Humanoid Tele-Loco-Manipulation Using Virtual Reality and Reinforcement Learning

Full-sized humanoid robot capabilities have grown exponentially in recent years, aiming towards general-purpose deployment in human environments. A popular control method used by manufacturers utilizes Virtual Reality for upper-body teleoperation and Reinforcement Learning for lower-body balance and locomotion control. As a result, a single remote operator can see, manipulate, and navigate about a real, distant physical environment. This powerful control stack is often relegated to expensive full-sized robots, many of which are inaccessible to the research community. Miniature humanoids are more prevalent, but employ less biomimicry in their design (e.g. fewer sensors, Degrees of Freedom, etc) and lack similar developments. This paper describes a compliant full-body telepresence control stack developed from the ground up for miniature humanoids. Framework experimentation on ROBOTIS OP3 hardware showcases walking at speeds up to 0.45 m/s independent of arm motions. Tele-loco-manipulation is demonstrated via a cube relocation experiment with an expert human operator. On average, the teleoperated system moved 2 different 40 g cubes within 10 mins, walking a total distance of 5 m. Overall, the developed system shows potential for miniature humanoid tele-loco-manipulation.

cs.RO↗

arXiv2026

Loco-Loco-RL: Low-Cost Terrain Mapping for Humanoid Locomotion with Reinforcement Learning

Informative terrain perception is important for robust reinforcement learning policies in humanoid locomotion. Still, common sensors such as depth cameras and LiDARs incur high cost, power, and processing overhead while often producing redundant, high-resolution data. This work uses a low-cost time-of-flight sensor to provide a compact 3D local terrain representation for humanoid locomotion. To efficiently use this sparse exteroceptive input, we introduce a token-compressed temporal transformer policy. Proprioceptive and terrain observations are tokenized and processed by a self-attention multi-head transformer to capture within-timestep relationships between observation terms. The attended tokens are then compressed through an MLP-based latent-space token compression module before being stored in a rolling 15-timestep history. A second cross-attention multi-head transformer extracts temporal locomotion features from this compact history for policy learning. By compressing tokens before temporal aggregation, the architecture preserves important terrain-observation structure while limiting the dimensional growth of attention over observation histories. We validate our method through sim-to-real transfer on physical hardware using a terrain-based locomotion benchmark, demonstrating robust humanoid terrain walking with low-cost local terrain sensing.

cs.RO↗

arXiv2026

Learning to Stack: Cube-Stacking Imitation Learning from Virtual Reality Demonstrations

Imitation learning is attractive for robot manipulation, but collecting demonstrations remains a bottleneck for multi-stage tasks requiring repeated scene resets. This work presents a virtual-reality data-collection pipeline for cube-stacking with a custom 5-DoF arm in NVIDIA Isaac Sim and Isaac Lab. Using an HTC Vive Pro 2, Manus Quantum gloves, and OpenXR, an operator provides SE(3) end-effector commands to generate task demonstrations. The proposed framework separates demonstration collection from dataset construction by replaying recorded trajectories, converting task-space commands into joint-space actions, and re-rendering demonstrations with updated sensor or state configurations. This allows previously collected demonstrations to be reused for new observation and action spaces without repeating human teleoperation. The task requires stacking the red cube on the blue cube and the green cube on the red cube, with randomized cube placement. In 30 minutes, 200 virtual demonstrations were collected, compared with 45 real-world demonstrations, and Isaac Mimic generated 100 additional samples. A behavior-cloning policy was trained from the virtual demonstrations using LeRobot-style dual-camera observations and evaluated in simulation.

cs.RO↗

arXiv2026

Isaac Sim-to-Real: Reinforcement Learning based Locomotion for Quadrupeds

Learning-based approaches to locomotion have risen in popularity in recent years, showing the capability for complex legged locomotion and whole-body control. Reinforcement learning (RL), the primary learning-based approach for locomotion, often utilizes a high-performance simulation tool, providing a controlled and efficient training and development environment. However, policies that perform well in simulation frequently encounter unexpected challenges when deployed on a physical system, known as the sim-to-real gap. This work presents a robust RL locomotion framework capable of whole-body control. The proposed RL framework utilizes Nvidia's new set of simulation tools, Isaac Sim, and its companion RL framework, Isaac Lab, for training, achieving a zero-shot sim-to-real policy. The performance of our policy is validated on physical hardware using the Unitree Go1, with experimental results showing similar velocity tracking performance to the quadruped's integrated controller, with a greater ability to recover from large disturbances, and achieve linear velocities of 2.0 m/s and angular velocities of 1.8 rad/s.

cs.RO↗

arXiv2026

Towards Torque-Driven Reinforcement Learning for Quadruped Locomotion

Reinforcement learning (RL) for legged robots is advancing locomotion, demonstrating its ability to adapt to new and challenging terrain. Traditionally, these RL locomotion frameworks are position-based, making the policy less adaptable to terrain types and requiring state estimation techniques in the observation space, i.e., linear velocity. Moreover, these RL frameworks often use small, lightweight quadrupeds that are limited in their viability for high-complexity tasks due to hardware constraints. This work explores an RL torque control framework for heavyweight high-torque quadrupeds. The RL framework in this paper can traverse rough terrain and effectively track a desired linear velocity without requiring knowledge of the agent's current velocity. Using Nvidia's Isaac Sim and Isaac Lab, simulation results of the RL torque control policy are shown on the Unitree B1 quadruped, achieving speeds of 3.5 m/s and 1.5 rad/s. In addition, the quadruped can walk up and down stairs without the aid of an exteroceptive sensor.

cs.RO↗