Computer Science · Literature

Research papers on Reinforcement learning in robotics

Recent and highly-cited academic work on reinforcement learning in robotics, gathered from Semantic Scholar, CrossRef and OpenAlex.

1. Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning

   Lukas Brunke, Melissa Greeff, Adam W. Hall, et al. · 2022 · Annual Review of Control, Robotics, and Autonomous Systems · 776 citations

   The last half decade has seen a steep rise in the number of contributions on safe learning methods for real-world robotic deployments from both the control and reinforcement learning communities. This article provides a concise but holistic review of the recent advances made in using machine learning to achieve safe decision-making under uncertainties, with a focus on unifying the language and frameworks used in control theory and reinforcement learning research. It includes learning-based control approaches that safely improve performance by learning the uncertain dynamics, reinforcement learning approaches that encourage safety or robustness, and methods that can formally certify the safet

   Save this paper

2. Control Policy with Autocorrelated Noise in Reinforcement Learning for Robotics

   Paweł Wawrzyński · 2015 · International Journal of Machine Learning and Computing · 38 citations

   Save this paper

3. A learning architecture based on reinforcement learning for adaptive control of the walking machine LAURON

   Winfried Ilg, Karsten Berns · 1995 · Robotics and Autonomous Systems · 38 citations

   Save this paper

4. Adaptive optimal control of stencil printing process using reinforcement learning

   Nourma Khader, Sang Won Yoon · 2021 · Robotics and Computer-Integrated Manufacturing · 26 citations

   Save this paper

5. Skillful control under uncertainty via direct reinforcement learning

   Vijaykumar Gullapalli · 1995 · Robotics and Autonomous Systems · 17 citations

   Save this paper

6. Addressing Challenges in Dynamic Modeling of Stewart Platform using Reinforcement Learning-Based Control Approach

   Hadi Yadavari, Vahid Tavakol Aghaei, Serhat İkizoğlu · 2024 · Journal of Robotics and Control (JRC) · 7 citations

   In this paper, we focus on enhancing the performance of the controller utilized in the Stewart platform by investigating the dynamics of the platform. Dynamic modeling is crucial for control and simulation, yet challenging for parallel robots like the Stewart platform due to closed-loop kinematics. We explore classical methods to solve its inverse dynamical model, but conventional approaches face difficulties, often resulting in simplified and inaccurate models. To overcome this limitation, we propose a novel approach by replacing the classical feedforward inverse dynamic block with a reinforcement learning (RL) agent, which, to our knowledge, has not been tried yet in the context of the Ste

   Save this paper

7. Consensus of Multi-agent Reinforcement Learning Systems: The Effect of Immediate Rewards

   Neshat Elhami Fard, Rastko Selmic · 2022 · Journal of Robotics and Control (JRC) · 6 citations

   This paper studies the consensus problem of a leaderless, homogeneous, multi-agent reinforcement learning (MARL) system using actor-critic algorithms with and without malicious agents. The goal of each agent is to reach the consensus position with the maximum cumulative reward. Although the reward function converges in both scenarios, in the absence of the malicious agent, the cumulative reward is higher than with the malicious agent present. We consider here various immediate reward functions. First, we study the immediate reward function based on Manhattan distance. In addition to proposing three different immediate reward functions based on Euclidean, $n$-norm, and Chebyshev distances, we

   Save this paper

8. Data-Driven Reinforcement Learning Control for Quadrotor Systems

   Ngoc Trung Dang, Phuong Nam Dao · 2024 · International Journal of Mechanical Engineering and Robotics Research · 3 citations

   This paper aims to solve the tracking problem and optimality effectiveness of an Unmanned Aerial Vehicle (UAV) by model-free data Reinforcement Learning (RL) algorithms in both sub-systems of attitude and position. First, a cascade UAV model structure is given to establish the control system diagram with two corresponding attitude and position control loops. Second, based on the computation of the time derivative of the Bellman function by two different methods, the combination of the Bellman function and the optimal control is adopted to maintain the control signal as time converges to infinity with the addition of a discount factor. Third, according to off policy technique, the two propose

   Save this paper

9. Robotic Arm Control Using a Q-Learning Reinforcement Algorithm

   Afonso M. Timóteo, Ramiro S. Barbosa, Isabel S. Jesus · 2026 · Robotics · 1 citations

   This paper presents the design and implementation of an integrated robotic system capable of detecting objects through computer vision and making decisions based on logic strategies to perform physical tasks. For that, the system uses a robotic arm to play the Tic-Tac-Toe game utilizing a Q-learning algorithm to determine optimal moves. The system can be controlled using a graphical interface that enables real-time monitoring, facilitating seamless interaction between the user and the robotic arm. Three algorithms with different decision strategies were developed: a random decision algorithm, the MiniMax algorithm, and Q-learning, a reinforcement-learning algorithm. The results obtained high

   Save this paper

10. Control of Dynamic Systems in Robotics Using Reinforcement Learning

    Dr. Emma J. Clarke · 2022 · American Journal of Instrumentation and Control Engineering

    The field of robotics has made significant strides in utilizing Reinforcement Learning (RL) for the control of dynamic systems, which are systems that evolve over time due to internal or external factors. Unlike traditional control techniques, RL allows robotic systems to learn from their environment and adapt to dynamic conditions without requiring an explicit model of the system. This article explores the application of RL in controlling dynamic robotic systems, focusing on tasks such as motion control, path planning, and robotic manipulation. We discuss key RL methods including Q-learning, Deep Q Networks (DQN), and Proximal Policy Optimization (PPO), and how these techniques are applied

    Save this paper