# Distributed Reinforcement Learning of Targeted Grasping with Active Vision for Mobile Manipulators

arXiv: https://arxiv.org/abs/2007.08082 · HTML: https://mlsanity.com/paper/2007.08082/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jul 2020.

## Built on by (most cited first, 7 of 7)

- [Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills](https://mlsanity.com/paper/2104.07749/) (2021)
- [Adaptive Rotated Convolution for Rotated Object Detection](https://mlsanity.com/paper/2303.07820/) (2023)
- [Computational Benefits of Intermediate Rewards for Goal-Reaching Policy Learning](https://mlsanity.com/paper/2107.03961/) (2021)
- [Understanding the Complexity Gains of Single-Task RL with a Curriculum](https://mlsanity.com/paper/2212.12809/) (2022)
- [On the Estimation Bias in Double Q-Learning](https://mlsanity.com/paper/2109.14419/) (2021)
- [Efficient Sparse-Reward Goal-Conditioned Reinforcement Learning with a High Replay Ratio and Regularization](https://mlsanity.com/paper/2312.05787/) (2023)
- [SENSOR: Imitate Third-Person Expert's Behaviors via Active Sensoring](https://mlsanity.com/paper/2404.03386/) (2024)

## Abstract (arXiv)

Developing personal robots that can perform a diverse range of manipulation tasks in unstructured environments necessitates solving several challenges for robotic grasping systems. We take a step towards this broader goal by presenting the first RL-based system, to our knowledge, for a mobile manipulator that can (a) achieve targeted grasping generalizing to unseen target objects, (b) learn complex grasping strategies for cluttered scenes with occluded objects, and (c) perform active vision through its movable wrist camera to better locate objects. The system is informed of the desired target object in the form of a single, arbitrary-pose RGB image of that object, enabling the system to generalize to unseen objects without retraining. To achieve such a system, we combine several advances in deep reinforcement learning and present a large-scale distributed training system using synchronous SGD that seamlessly scales to multi-node, multi-GPU infrastructure to make rapid prototyping easier. We train and evaluate our system in a simulated environment, identify key components for improving performance, analyze its behaviors, and transfer to a real-world setup.