English
Related papers

Related papers: End-to-End Training of Deep Visuomotor Policies

200 papers

In principle, reinforcement learning and policy search methods can enable robots to learn highly complex and general skills that may allow them to function amid the complexity and diversity of the real world. However, training a policy that…

Machine Learning · Computer Science 2019-05-29 Ali Yahya , Adrian Li , Mrinal Kalakrishnan , Yevgen Chebotar , Sergey Levine

Robots need to learn skills that can not only generalize across similar problems but also be directed to a specific goal. Previous methods either train a new skill for every different goal or do not infer the specific target in the presence…

The physical design of a robot and the policy that controls its motion are inherently coupled, and should be determined according to the task and environment. In an increasing number of applications, data-driven and learning-based…

Robotics · Computer Science 2018-09-18 Charles Schaff , David Yunis , Ayan Chakrabarti , Matthew R. Walter

Vision-based robotics often separates the control loop into one module for perception and a separate module for control. It is possible to train the whole system end-to-end (e.g. with deep RL), but doing it "from scratch" comes with a high…

Robotics · Computer Science 2020-11-16 Bryan Chen , Alexander Sax , Gene Lewis , Iro Armeni , Silvio Savarese , Amir Zamir , Jitendra Malik , Lerrel Pinto

Deep networks trained on demonstrations of human driving have learned to follow roads and avoid obstacles. However, driving policies trained via imitation learning cannot be controlled at test time. A vehicle trained end-to-end to imitate…

Robotics · Computer Science 2018-03-05 Felipe Codevilla , Matthias Müller , Antonio López , Vladlen Koltun , Alexey Dosovitskiy

The common approach for local navigation on challenging environments with legged robots requires path planning, path following and locomotion, which usually requires a locomotion control policy that accurately tracks a commanded velocity.…

Robotics · Computer Science 2022-09-27 Nikita Rudin , David Hoeller , Marko Bjelonic , Marco Hutter

Multi-robot navigation is a challenging task in which multiple robots must be coordinated simultaneously within dynamic environments. We apply deep reinforcement learning (DRL) to learn a decentralized end-to-end policy which maps raw…

Robotics · Computer Science 2022-09-08 Christian Jestel , Hartmut Surmann , Jonas Stenzel , Oliver Urbann , Marius Brehler

Control policy learning for modular robot locomotion has previously been limited to proprioceptive feedback and flat terrain. This paper develops policies for modular systems with vision traversing more challenging environments. These…

Robotics · Computer Science 2023-05-02 Julian Whitman , Howie Choset

In this work, we study vision-based end-to-end reinforcement learning on vehicle control problems, such as lane following and collision avoidance. Our controller policy is able to control a small-scale robot to follow the right-hand lane of…

Machine Learning · Computer Science 2020-12-15 András Kalapos , Csaba Gór , Róbert Moni , István Harmati

Policy learning for partially observed control tasks requires policies that can remember salient information from past observations. In this paper, we present a method for learning policies with internal memory for high-dimensional,…

Machine Learning · Computer Science 2015-09-24 Marvin Zhang , Zoe McCarthy , Chelsea Finn , Sergey Levine , Pieter Abbeel

In this work we propose a novel end-to-end imitation learning approach which combines natural language, vision, and motion information to produce an abstract representation of a task, which in turn is used to synthesize specific motion…

Robotics · Computer Science 2019-11-27 Simon Stepputtis , Joseph Campbell , Mariano Phielipp , Chitta Baral , Heni Ben Amor

Autonomous drones can operate in remote and unstructured environments, enabling various real-world applications. However, the lack of effective vision-based algorithms has been a stumbling block to achieving this goal. Existing systems…

Robotics · Computer Science 2022-10-28 Jiawei Fu , Yunlong Song , Yan Wu , Fisher Yu , Davide Scaramuzza

The combination of deep neural network models and reinforcement learning algorithms can make it possible to learn policies for robotic behaviors that directly read in raw sensory inputs, such as camera images, effectively subsuming both…

Machine Learning · Computer Science 2019-05-17 Avi Singh , Larry Yang , Kristian Hartikainen , Chelsea Finn , Sergey Levine

Robust perception-action models should be learned from training data with diverse visual appearances and realistic behaviors, yet current approaches to deep visuomotor policy learning have been generally limited to in-situ models learned…

Computer Vision and Pattern Recognition · Computer Science 2017-07-25 Huazhe Xu , Yang Gao , Fisher Yu , Trevor Darrell

Autonomous UAV racing has recently emerged as an interesting research problem. The dream is to beat humans in this new fast-paced sport. A common approach is to learn an end-to-end policy that directly predicts controls from raw images by…

Robotics · Computer Science 2019-04-19 Matthias Müller , Guohao Li , Vincent Casser , Neil Smith , Dominik L. Michels , Bernard Ghanem

Sim-to-real transfer remains a fundamental challenge in robot manipulation due to the entanglement of perception and control in end-to-end learning. We present a decoupled framework that learns each component where it is most reliable:…

Robotics · Computer Science 2025-10-01 Jialei Huang , Zhaoheng Yin , Yingdong Hu , Shuo Wang , Xingyu Lin , Yang Gao

One of the great promises of robot learning systems is that they will be able to learn from their mistakes and continuously adapt to ever-changing environments. Despite this potential, most of the robot learning systems today are deployed…

Machine Learning · Computer Science 2020-08-03 Ryan Julian , Benjamin Swanson , Gaurav S. Sukhatme , Sergey Levine , Chelsea Finn , Karol Hausman

Skilled robot task learning is best implemented by predictive action policies due to the inherent latency of sensorimotor processes. However, training such predictive policies is challenging as it involves finding a trajectory of motor…

Robotics · Computer Science 2017-03-03 Ali Ghadirzadeh , Atsuto Maki , Danica Kragic , Mårten Björkman

Most policy search algorithms require thousands of training episodes to find an effective policy, which is often infeasible with a physical robot. This survey article focuses on the extreme other end of the spectrum: how can a robot adapt…

Training end-to-end deep robot policies requires a lot of domain-, task-, and hardware-specific data, which is often costly to provide. In this work, we propose to tackle this issue by employing a deep neural network with a modular…

Robotics · Computer Science 2019-03-12 Aleksi Hämäläinen , Karol Arndt , Ali Ghadirzadeh , Ville Kyrki
‹ Prev 1 2 3 10 Next ›