# Deep Reinforcement Learning with anticipatory reward in LSTM for Collision Avoidance of Mobile Robots

arXiv: https://arxiv.org/abs/2508.07941 · HTML: https://mlsanity.com/paper/2508.07941/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for robot navigation and UAV control, one of 15 directions in Deep reinforcement learning methods.
- Builds on 5 of its 23 references that are in the map.
- First posted on arXiv 11 Aug 2025.

## Placed in

- Deep reinforcement learning methods / [RL for robot navigation and UAV control](https://mlsanity.com/deeprl/rl-for-robot-navigation-and-uav-control/)

## Builds on (most cited first, 5 of 5)

- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [Decentralized Non-communicating Multiagent Collision Avoidance with Deep Reinforcement Learning](https://mlsanity.com/paper/1609.07845/) (2016)
- [Decentralized Probabilistic Multi-Robot Collision Avoidance Using Buffered Uncertainty-Aware Voronoi Cells](https://mlsanity.com/paper/2201.04012/) (2022)
- [Obstacle Avoidance and Navigation Utilizing Reinforcement Learning with Reward Shaping](https://mlsanity.com/paper/2003.12863/) (2020)
- [Distributed Computing by Mobile Robots: Uniform Circle Formation](https://mlsanity.com/paper/1407.5917/) (2014)

## Abstract (arXiv)

This article proposes a collision risk anticipation method based on short-term prediction of the agents position. A Long Short-Term Memory (LSTM) model, trained on past trajectories, is used to estimate the next position of each robot. This prediction allows us to define an anticipated collision risk by dynamically modulating the reward of a Deep Q-Learning Network (DQN) agent. The approach is tested in a constrained environment, where two robots move without communication or identifiers. Despite a limited sampling frequency (1 Hz), the results show a significant decrease of the collisions number and a stability improvement. The proposed method, which is computationally inexpensive, appears particularly attractive for implementation on embedded systems.