English
Related papers

Related papers: SDS -- See it, Do it, Sorted: Quadruped Skill Synt…

200 papers

Legged robots are becoming increasingly powerful and popular in recent years for their potential to bring the mobility of autonomous agents to the next level. This work presents a deep reinforcement learning approach that learns a robust…

Robotics · Computer Science 2021-09-10 Zhaocheng Liu , Fernando Acero , Zhibin Li

Learning from Demonstration (LfD) is a popular approach to endowing robots with skills without having to program them by hand. Typically, LfD relies on human demonstrations in clutter-free environments. This prevents the demonstrations from…

Robotics · Computer Science 2018-08-07 Muhammad Asif Rana , Mustafa Mukadam , Seyed Reza Ahmadzadeh , Sonia Chernova , Byron Boots

This article proposes a method for learning and robotic replication of dynamic collaborative tasks from offline videos. The objective is to extend the concept of learning from demonstration (LfD) to dynamic scenarios, benefiting from widely…

Robotics · Computer Science 2022-04-11 Francesco Iodice , Yuqiang Wu , Wansoo Kim , Fei Zhao , Elena De Momi , Arash Ajoudani

Integrating robots in complex everyday environments requires a multitude of problems to be solved. One crucial feature among those is to equip robots with a mechanism for teaching them a new task in an easy and natural way. When teaching…

Machine Learning · Computer Science 2021-03-29 Daniel Tanneberg , Kai Ploeger , Elmar Rueckert , Jan Peters

Learning from Demonstration (LfD) approaches empower end-users to teach robots novel tasks via demonstrations of the desired behaviors, democratizing access to robotics. A key challenge in LfD research is that users tend to provide…

Machine Learning · Computer Science 2022-02-16 Sravan Jayanthi , Letian Chen , Matthew Gombolay

Quadruped robots are progressively being integrated into human environments. Despite the growing locomotion capabilities of quadrupedal robots, their interaction with objects in realistic scenes is still limited. While additional robotic…

Robotics · Computer Science 2024-08-05 Zhengmao He , Kun Lei , Yanjie Ze , Koushil Sreenath , Zhongyu Li , Huazhe Xu

Gaits and transitions are key components in legged locomotion. For legged robots, describing and reproducing gaits as well as transitions remain longstanding challenges. Reinforcement learning has become a powerful tool to formulate…

Robotics · Computer Science 2022-01-04 Yecheng Shao , Yongbin Jin , Xianwei Liu , Weiyan He , Hongtao Wang , Wei Yang

Dynamical Systems (DS) are an effective and powerful means of shaping high-level policies for robotics control. They provide robust and reactive control while ensuring the stability of the driving vector field. The increasing complexity of…

Robotics · Computer Science 2024-03-19 Bernardo Fichera , Aude Billard

Learning from Demonstration (LfD) has emerged as a crucial method for robots to acquire new skills. However, when given suboptimal task trajectory demonstrations with shape characteristics reflecting human preferences but subpar dynamic…

Robotics · Computer Science 2025-04-21 Chenlin Ming , Zitong Wang , Boxuan Zhang , Zhanxiang Cao , Xiaoming Duan , Jianping He

Parkour is a grand challenge for legged locomotion that requires robots to overcome various obstacles rapidly in complex environments. Existing methods can generate either diverse but blind locomotion skills or vision-based but specialized…

We study the problem of unsupervised skill discovery, whose goal is to learn a set of diverse and useful skills with no external reward. There have been a number of skill discovery methods based on maximizing the mutual information (MI)…

Machine Learning · Computer Science 2022-02-09 Seohong Park , Jongwook Choi , Jaekyeom Kim , Honglak Lee , Gunhee Kim

A novel skill learning approach is proposed that allows a robot to acquire human-like visuospatial skills for object manipulation tasks. Visuospatial skills are attained by observing spatial relationships among objects through…

Robotics · Computer Science 2017-06-06 S. Reza Ahmadzadeh , Fulvio Mastrogiovanni , Petar Kormushev

As the number of the robot's degrees of freedom increases, the implementation of robot motion becomes more complex and difficult. In this study, we focus on learning 6DOF-grasping motion and consider dividing the grasping motion into…

Robotics · Computer Science 2021-03-24 Daichi Kawakami , Ryoichi Ishikawa , Menandro Roxas , Yoshihiro Sato , Takeshi Oishi

Like mammals, robots must rapidly learn to control their bodies and interact with their environment despite incomplete knowledge of their body structure and surroundings. They must also adapt to continuous changes in both. This work…

Legged robots are able to navigate complex terrains by continuously interacting with the environment through careful selection of contact sequences and timings. However, the combinatorial nature behind contact planning hinders the…

Designing reward functions for agile robotic maneuvers in reinforcement learning remains difficult, and demonstration-based approaches often require reference motions that are unavailable for novel platforms or extreme stunts. We present…

Robotics · Computer Science 2026-05-11 Seungeun Rho , Shamel Fahmi , Jeonghwan Kim , Arianna Ilvonen , Sehoon Ha , Gabriel Nelson

Legged robots must adapt their gait to navigate unpredictable environments, a challenge that animals master with ease. However, most deep reinforcement learning (DRL) approaches to quadruped locomotion rely on a fixed gait, limiting…

Robotics · Computer Science 2025-06-24 Joseph Humphreys , Chengxu Zhou

Learning for Demonstration (LfD) enables robots to acquire new skills by imitating expert demonstrations, allowing users to communicate their instructions in an intuitive manner. Recent progress in LfD often relies on kinesthetic teaching…

Robotics · Computer Science 2024-04-02 Weiming Zhi , Tianyi Zhang , Matthew Johnson-Roberson

Humanoid robots promise transformative capabilities for industrial and service applications. While recent advances in Reinforcement Learning (RL) yield impressive results in locomotion, manipulation, and navigation, the proposed methods…

Robotics · Computer Science 2025-08-12 Feiyang Wu , Xavier Nal , Jaehwi Jang , Wei Zhu , Zhaoyuan Gu , Anqi Wu , Ye Zhao

Reinforcement learning necessitates meticulous reward shaping by specialists to elicit target behaviors, while imitation learning relies on costly task-specific data. In contrast, unsupervised skill discovery can potentially reduce these…

Robotics · Computer Science 2026-02-11 Ruopeng Cui , Yifei Bi , Haojie Luo , Wei Li