English
Related papers

Related papers: Toward Reliable Sim-to-Real Predictability for MoE…

200 papers

This paper presents reinforcement learning (RL) policies for dynamic quadrupedal locomotion in planetary exploration scenarios. Building on a taskoptimized quadruped with a 5-bar leg design, we develop RL policies for walking, vertical…

Robotics · Computer Science 2026-05-26 Jørgen Anker Olsen , Kostas Alexis

Real-time whole-body teleoperation is a critical method for humanoid robots to perform complex tasks in unstructured environments. However, developing a unified controller that robustly supports diverse human motions remains a significant…

Robotics · Computer Science 2026-05-14 Jie Li , Bing Tang , Feng Wu

This paper addresses the challenge of terrain-adaptive dynamic locomotion in humanoid robots, a problem traditionally tackled by optimization-based methods or reinforcement learning (RL). Optimization-based methods, such as model-predictive…

Robotics · Computer Science 2024-07-30 Shangqun Yu , Nisal Perera , Daniel Marew , Donghyun Kim

Agile-legged robots have proven to be highly effective in navigating and performing tasks in complex and challenging environments, including disaster zones and industrial settings. However, these applications normally require the capability…

Robotics · Computer Science 2024-04-09 Mohsen Sombolestan , Quan Nguyen

Legged robots can traverse a wide variety of terrains, some of which may be challenging for wheeled robots, such as stairs or highly uneven surfaces. However, quadruped robots face stability challenges on slippery surfaces. This can be…

As machine learning models in critical fields increasingly grapple with multimodal data, they face the dual challenges of handling a wide array of modalities, often incomplete due to missing elements, and the temporal irregularity and…

Machine Learning · Computer Science 2025-04-10 Xing Han , Huy Nguyen , Carl Harris , Nhat Ho , Suchi Saria

This work aims to push the limits of agility for bipedal robots by enabling a torque-controlled bipedal robot to perform robust and versatile dynamic jumps in the real world. We present a reinforcement learning framework for training a…

Robotics · Computer Science 2023-06-02 Zhongyu Li , Xue Bin Peng , Pieter Abbeel , Sergey Levine , Glen Berseth , Koushil Sreenath

Generating dynamic motions for legged robots remains a challenging problem. While reinforcement learning has achieved notable success in various legged locomotion tasks, producing highly dynamic behaviors often requires extensive reward…

Robotics · Computer Science 2026-01-01 Dongyun Kang , Min-Gyu Kim , Tae-Gyu Song , Hajun Kim , Sehoon Ha , Hae-Won Park

Adapting large-scale foundation models in multi-task scenarios often suffers from task conflict and oblivion. To mitigate such issues, we propose a novel ''model MoE-ization'' strategy that leads to a conflict- and oblivion-resistant…

Machine Learning · Computer Science 2025-10-28 Shen Yuan , Yin Zheng , Taifeng Wang , Binbin Liu , Hongteng Xu

Sim-to-real reinforcement learning (RL) for humanoid robots with high-gear ratio actuators remains challenging due to complex actuator dynamics and the absence of torque sensors. To address this, we propose a novel RL framework leveraging…

Robotics · Computer Science 2025-04-14 Sotaro Katayama , Yuta Koda , Norio Nagatsuka , Masaya Kinoshita

Recently, quadrupedal locomotion has achieved significant success, but their manipulation capabilities, particularly in handling large objects, remain limited, restricting their usefulness in demanding real-world applications such as search…

Robotics · Computer Science 2025-04-01 Yuming Feng , Chuye Hong , Yaru Niu , Shiqi Liu , Yuxiang Yang , Wenhao Yu , Tingnan Zhang , Jie Tan , Ding Zhao

We focus on agile, continuous, and terrain-adaptive jumping of quadrupedal robots in discontinuous terrains such as stairs and stepping stones. Unlike single-step jumping, continuous jumping requires accurately executing highly dynamic…

Current autonomous driving systems often favor end-to-end frameworks, which take sensor inputs like images and learn to map them into trajectory space via neural networks. Previous work has demonstrated that models can achieve better…

Computer Vision and Pattern Recognition · Computer Science 2025-12-10 Zebin Xing , Pengxuan Yang , Linbo Wang , Yichen Zhang , Yiming Hu , Yupeng Zheng , Junli Wang , Yinfeng Gao , Guang Li , Kun Ma , Long Chen , Zhongpu Xia , Qichao Zhang , Hangjun Ye , Dongbin Zhao

Quadrotors are highly nonlinear dynamical systems that require carefully tuned controllers to be pushed to their physical limits. Recently, learning-based control policies have been proposed for quadrotors, as they would potentially allow…

Robotics · Computer Science 2022-02-23 Elia Kaufmann , Leonard Bauersfeld , Davide Scaramuzza

This article presents Platform Adaptive Locomotion (PAL), a unified control method for quadrupedal robots with different morphologies and dynamics. We leverage deep reinforcement learning to train a single locomotion policy on procedurally…

Robotics · Computer Science 2025-07-11 David Rytz , Suyoung Choi , Wanming Yu , Wolfgang Merkt , Jemin Hwangbo , Ioannis Havoutis

Developing natural and diverse locomotion controllers for quadruped robots that can adapt to complex terrains while preserving motion style remains a significant challenge. Existing imitation-based methods face a fundamental optimization…

Robotics · Computer Science 2026-04-21 Zhiquan Wang , Yunyu Liu , Dipam Patel , Ayush Kumar , Aniket Bera , Bedrich Benes

The semantics of the environment, such as the terrain type and property, reveals important information for legged robots to adjust their behaviors. In this work, we present a framework that learns semantics-aware locomotion skills from…

Robotics · Computer Science 2022-10-12 Yuxiang Yang , Xiangyun Meng , Wenhao Yu , Tingnan Zhang , Jie Tan , Byron Boots

In this paper, with a view toward fast deployment of locomotion gaits in low-cost hardware, we use a linear policy for realizing end-foot trajectories in the quadruped robot, Stoch $2$. In particular, the parameters of the end-foot…

Recent progress in two-view geometry increasingly emphasizes enforcing smoothness and global consistency priors when estimating motion fields between pairs of images. However, in complex real-world scenes, characterized by extreme viewpoint…

Computer Vision and Pattern Recognition · Computer Science 2025-08-04 Jiajun Le , Jiayi Ma

Deep reinforcement learning has recently achieved strong results in quadrupedal locomotion, yet policies trained in simulation often fail to transfer when the environment changes. Evolutionary reinforcement learning aims to address this…

Robotics · Computer Science 2026-04-09 Brian McAteer , Karl Mason