Nikita Rudin

Last Name

Rudin

First Name

Nikita

ORCID

0000-0001-5893-0348

Show all metadata

Search Results

Publications 1 - 10 of 13

Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments
Mittal, Mayank; Yu, Calvin; Yu, Qinxi; et al. (2023)
IEEE Robotics and Automation Letters
We present Orbit, a unified and modular framework for robot learning powered by Nvidia Isaac Sim. It offers a modular design to easily and efficiently create robotic environments with photo-realistic scenes and high-fidelity rigid and deformable body simulation. With Orbit, we provide a suite of benchmark tasks of varying difficulty- from single-stage cabinet opening and cloth folding to multi-stage tasks such as room reorganization. To support working with diverse observations and action spaces, we include fixed-arm and mobile manipulators with different physically-based sensors and motion generators. Orbit allows training reinforcement learning policies and collecting large demonstration datasets from hand-crafted or expert solutions in a matter of minutes by leveraging GPU-based parallelization. In summary, we offer an open-sourced framework that readily comes with 16 robotic platforms, 4 sensor modalities, 10 motion generators, more than 20 benchmark tasks, and wrappers to 4 learning libraries. With this framework, we aim to support various research areas, including representation learning, reinforcement learning, imitation learning, and task and motion planning. We hope it helps establish interdisciplinary collaborations in these communities, and its modularity makes it easily extensible for more tasks and applications in the future.
Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning
Rudin, Nikita; Hoeller, David; Reist, Philipp; et al. (2022)
Proceedings of Machine Learning Research ~ Proceedings of the 5th Conference on Robot Learning
In this work, we present and study a training set-up that achieves fast policy generation for real-world robotic tasks by using massive parallelism on a single workstation GPU. We analyze and discuss the impact of different training algorithm components in the massively parallel regime on the final policy performance and training times. In addition, we present a novel game-inspired curriculum that is well suited for training with thousands of simulated robots in parallel. We evaluate the approach by training the quadrupedal robot ANYmal to walk on challenging terrain. The parallel approach allows training policies for flat terrain in under four minutes, and in twenty minutes for uneven terrain. This represents a speedup of multiple orders of magnitude compared to previous work. Finally, we transfer the policies to the real robot to validate the approach. We open-source our training code to help accelerate further research in the field of learned legged locomotion: https://leggedrobotics.github.io/legged_gym/.
Learning Agile Locomotion on Risky Terrains
Zhang, Chong; Rudin, Nikita; Hoeller, David; et al. (2024)
2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Quadruped robots have shown remarkable mobility on various terrains through reinforcement learning. Yet, in the presence of sparse footholds and risky terrains such as stepping stones and balance beams, which require precise foot placement to avoid falls, model-based approaches are often used. In this paper, we show that end-to-end reinforcement learning can also enable the robot to traverse risky terrains with dynamic motions. To this end, our approach involves training a generalist policy for agile locomotion on disorderly and sparse stepping stones before transferring its reusable knowledge to various more challenging terrains by finetuning specialist policies from it. Given that the robot needs to rapidly adapt its velocity on these terrains, we formulate the task as a navigation task instead of the commonly used velocity tracking which constrains the robot's behavior and propose an exploration strategy to overcome sparse rewards and achieve high robustness. We validate our proposed method through simulation and real-world experiments on an ANYmal-D robot achieving peak forward velocity of >= 2.5 m/s on sparse stepping stones and narrow balance beams. Video: youtu.be/Z5X0J8OH6z4
Barry: A High-Payload and Agile Quadruped Robot
Valsecchi, Giorgio; Rudin, Nikita; Nachtigall, Lennart; et al. (2023)
IEEE Robotics and Automation Letters
This letter introduces Barry, a dynamically balancing quadruped robot optimized for high payload capabilities and efficiency. It presents a new high-torque and low-inertia leg design, which includes custom-built high-efficiency actuators and transparent, sensorless transmissions. The robot's reinforcement learning-based controller is trained to fully leverage the new hardware capabilities to balance and steer the robot. The newly developed controller can manage the non-linearities introduced by the new leg design and handle unmodeled payloads up to 90 kg while operating at high efficiency. The approach's efficacy is demonstrated by a high payload-to-weight ratio verified with multiple tests, with a maximum ratio of 2 on flat terrain. Experiments also demonstrate Barry's power consumption and cost of transport, which converge to a value of 0.7 at 1.4 m/s, regardless of the payload mass.
Advanced Skills through Multiple Adversarial Motion Priors in Reinforcement Learning
Vollenweider, Eric; Bjelonic, Marko; Klemm, Victor; et al. (2023)
2023 IEEE International Conference on Robotics and Automation (ICRA)
Reinforcement learning (RL) has emerged as a powerful approach for locomotion control of highly articulated robotic systems. However, one major challenge is the tedious process of tuning the reward function to achieve the desired motion style. To address this issue, imitation learning approaches such as adversarial motion priors have been proposed, which encourage a pre-defined motion style. In this work, we present an approach to enhance the concept of adversarial motion prior-based RL, allowing for multiple, discretely switchable motion styles. Our approach demonstrates that multiple styles and skills can be learned simultaneously without significant performance differences, even in combination with motion data-free skills. We conducted several real-world experiments using a wheeled-legged robot to validate our approach. The experiments involved learning skills from existing RL controllers and trajectory optimization, such as ducking and walking, as well as novel skills, such as switching between a quadrupedal and humanoid configuration. For the latter skill, the robot was required to stand up, navigate on two wheels, and sit down. Instead of manually tuning the sit-down motion, we found that a reverse playback of the stand-up movement helped the robot discover feasible sit-down behaviors and avoided the need for tedious reward function tuning.
Generalizing Agile Legged Locomotion with Deep Reinforcement Learning
Rudin, Nikita (2025)
Neural Scene Representation for Locomotion on Structured Terrain
Hoeller, David; Rudin, Nikita; Choy, Christopher; et al. (2022)
IEEE Robotics and Automation Letters
ANYmal parkour: Learning agile navigation for quadrupedal robots
Hoeller, David; Rudin, Nikita; Sako, Dhionis; et al. (2024)
Science Robotics
Performing agile navigation with four-legged robots is a challenging task because of the highly dynamic motions, contacts with various parts of the robot, and the limited field of view of the perception sensors. Here, we propose a fully learned approach to training such robots and conquer scenarios that are reminiscent of parkour challenges. The method involves training advanced locomotion skills for several types of obstacles, such as walking, jumping, climbing, and crouching, and then using a high-level policy to select and control those skills across the terrain. Thanks to our hierarchical formulation, the navigation policy is aware of the capabilities of each skill, and it will adapt its behavior depending on the scenario at hand. In addition, a perception module was trained to reconstruct obstacles from highly occluded and noisy sensory data and endows the pipeline with scene understanding. Compared with previous attempts, our method can plan a path for challenging scenarios without expert demonstration, offline computation, a priori knowledge of the environment, or taking contacts explicitly into account. Although these modules were trained from simulated data only, our real-world experiments demonstrate successful transfer on hardware, where the robot navigated and crossed consecutive challenging obstacles with speeds of up to 2 meters per second.
Resilient Legged Local Navigation: Learning to Traverse with Compromised Perception End-to-End
Zhang, Chong; Jin, Jin; Frey, Jonas; et al. (2024)
2024 IEEE International Conference on Robotics and Automation (ICRA)
Autonomous robots must navigate reliably in un known environments even under compromised exteroceptive perception, or perception failures. Such failures often occur when harsh environments lead to degraded sensing, or when the perception algorithm misinterprets the scene due to limited generalization. In this paper, we model perception failures as invisible obstacles and pits, and train a reinforcement learning (RL) based local navigation policy to guide our legged robot. Unlike previous works relying on heuristics and anomaly detection to update navigational information, we train our navigation policy to reconstruct the environment information in the latent space from corrupted perception and react to perception failures end-to-end. To this end, we incorporate both proprioception and exteroception into our policy inputs, thereby enabling the policy to sense collisions on different body parts and pits, prompting corresponding reactions. We validate our approach in simulation and on the real quadruped robot ANYmal running in real-time (<10 ms CPU inference). In a quantitative comparison with existing heuristic-based locally reactive planners, our policy increases the success rate over 30 % when facing perception failures. Project Page: https: //bit.ly/45NBTuh
Optimal Global Path Planning for Multimodel Locomotion on Lunar Terrain
Wells, Sandra C.; Zhang, Peter; Kolvenbach, Hendrik; et al. (2022)
Proceedings of ASTRA 2022
Identifying robotic traverses on the surface of other celestial bodies is essential to assess the capabilities of the required system at the mission planning stage. With increasingly diverse robotic systems designs for space, including wheeled, walking, and multimodal systems, a wider range of behaviors concerning electrical energy consumption and failure risk are becoming available. Thus, it becomes necessary to define path optimality for the two parameters individually, beyond a traditional minimization of path length. This paper proposes a path planning algorithm that finds optimal global paths on the lunar surface for robotic energy consumption and risk, where the user can define the energy and risk minimization functions and their relative importance. Based on a custom A* implementation, the proposed algorithm successfully minimizes the energy consumption and path risk in various scenarios. Exemplary, a cost function for the walking robot ANYmal was generated in simulation and applied to our planner. The results show that different optimized global paths were generated depending on the user’s energy/risk trade-off.

Publications 1 - 10 of 13

Nikita Rudin

Last Name

First Name

ORCID

Organisational unit

Filters

Search Results