A Reinforcement Learning Approach to Non-prehensile Manipulation through Sliding
On the map: Deep reinforcement learning methods → RL for robot locomotion and manipulation
Abstract (arXiv)
Although robotic applications increasingly demand versatile and dynamic object handling, most existing techniques are predominantly focused on grasp-based manipulation, limiting their applicability in non-prehensile tasks. To address this need, this study introduces a Deep Deterministic Policy Gradient (DDPG) reinforcement learning framework for efficient non-prehensile manipulation, specifically for sliding an object on a surface. The algorithm generates a linear trajectory by precisely controlling the acceleration of a robotic arm rigidly coupled to the horizontal surface, enabling the relative manipulation of an object as it slides on top of the surface. Furthermore, two distinct algorithms have been developed to estimate the frictional forces dynamically during the sliding process. These algorithms provide online friction estimates after each action, which are fed back into the actor model as critical feedback after each action. This feedback mechanism enhances the policy's adaptability and robustness, ensuring more precise control of the platform's acceleration in response to varying surface condition. The proposed algorithm is validated through simulations and real-world experiments. Results demonstrate that the proposed framework effectively generalizes sliding manipulation across varying distances and, more importantly, adapts to different surfaces with diverse frictional properties. Notably, the trained model exhibits zero-shot sim-to-real transfer capabilities.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods. Builds on 15 of its 36 references that are in the map. First posted on arXiv 24 Feb 2025.
Builds on
15 of 36 references.
References · 15
- 2017Proximal Policy Optimization Algorithmscited by 15,215
- 2015Continuous control with deep reinforcement learningcited by 3,407
- 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,417
- 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,498
- 2021Understanding Domain Randomization for Sim-to-real Transfercited by 80
- 2021Long-Horizon Manipulation of Unknown Objects via Task and Motion Planning with Estimated Affordancescited by 40
- 2024Demonstrating Agile Flight from Pixels without State Estimationcited by 31
- 2023HACMan: Learning Hybrid Actor-Critic Maps for 6D Non-Prehensile Manipulationcited by 29
- 2023Domain Randomization via Entropy Maximizationcited by 19
- 2023Nonprehensile Planar Manipulation through Reinforcement Learning with Multimodal Categorical Explorationcited by 9
- 2018A Data-Efficient Approach to Precise and Controlled Pushingcited by 7
- 2023Keep it Upright: Model Predictive Control for Nonprehensile Object Transportation with Obstacle Avoidance on a Mobile Manipulatorcited by 5
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024Learning Visuotactile Estimation and Control for Non-prehensile Manipulation under Occlusions
- 2026Contact-Guided Exploration for Non-Prehensile Locomanipulation with Multi-Critic RL ↗
- 2025Learning Pivoting Manipulation with Force and Vision Feedback Using Optimization-based Demonstrations
- 2025DyWA: Dynamics-adaptive World Action Model for Generalizable Non-prehensile Manipulation
- 2026Non-Prehensile Throwing: A Reinforcement Learning Perspective
- 2025PIN-WM: Learning Physics-INformed World Models for Non-Prehensile Manipulation
- 2025Dynamic object goal pushing with mobile manipulators through model-free constrained reinforcement learning
- 2025Robot Deformable Object Manipulation via NMPC-generated Demonstrations in Deep Reinforcement Learning