# Multi-agent Motion Planning for Dense and Dynamic Environments via Deep Reinforcement Learning

arXiv: https://arxiv.org/abs/2001.06627 · HTML: https://mlsanity.com/paper/2001.06627/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jan 2020.

## Built on by (most cited first, 21 of 21)

- [Learning Interaction-Aware Trajectory Predictions for Decentralized Multi-Robot Motion Planning in Dynamic Environments](https://mlsanity.com/paper/2102.05382/) (2021)
- [DR-MPC: Deep Residual Model Predictive Control for Real-world Social Navigation](https://mlsanity.com/paper/2410.10646/) (2024)
- [Discrete GCBF Proximal Policy Optimization for Multi-agent Safe Optimal Control](https://mlsanity.com/paper/2502.03640/) (2025)
- [DC-MRTA: Decentralized Multi-Robot Task Allocation and Navigation in Complex Environments](https://mlsanity.com/paper/2209.02865/) (2022)
- [Autonomous Driving in Unstructured Environments: How Far Have We Come?](https://mlsanity.com/paper/2410.07701/) (2024)
- [E-MAPP: Efficient Multi-Agent Reinforcement Learning with Parallel Program Guidance](https://mlsanity.com/paper/2212.02064/) (2022)
- [Learning Team-Based Navigation: A Review of Deep Reinforcement Learning Techniques for Multi-Agent Pathfinding](https://mlsanity.com/paper/2308.05893/) (2023)
- [Solving Multi-Agent Safe Optimal Control with Distributed Epigraph Form MARL](https://mlsanity.com/paper/2504.15425/) (2025)
- [Multi-agent Soft Actor-Critic Based Hybrid Motion Planner for Mobile Robots](https://mlsanity.com/paper/2112.06594/) (2021)
- [Safe multi-agent motion planning under uncertainty for drones using filtered reinforcement learning](https://mlsanity.com/paper/2311.00063/) (2023)
- [Nearest-Neighbor-based Collision Avoidance for Quadrotors via Reinforcement Learning](https://mlsanity.com/paper/2104.14912/) (2021)
- [Variational Meta Reinforcement Learning for Social Robotics](https://mlsanity.com/paper/2206.03211/) (2022)
- [Importance Sampling-Guided Meta-Training for Intelligent Agents in Highly Interactive Environments](https://mlsanity.com/paper/2407.15839/) (2024)
- [Evolutionary Curriculum Training for DRL-Based Navigation Systems](https://mlsanity.com/paper/2306.08870/) (2023)
- [Mixed-Reality Digital Twins: Leveraging the Physical and Virtual Worlds for Hybrid Sim2Real Transition of Multi-Agent Reinforcement Learning Policies](https://mlsanity.com/paper/2403.10996/) (2024)
- [Dyna-LfLH: Learning Agile Navigation in Dynamic Environments from Learned Hallucination](https://mlsanity.com/paper/2403.17231/) (2024)
- [Multi-robot Social-aware Cooperative Planning in Pedestrian Environments Using Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2211.15901/) (2022)
- [Multi-Agent Deep Reinforcement Learning for Cooperative and Competitive Autonomous Vehicles using AutoDRIVE Ecosystem](https://mlsanity.com/paper/2309.10007/) (2023)
- [Improving the Generalization of Unseen Crowd Behaviors for Reinforcement Learning based Local Motion Planners](https://mlsanity.com/paper/2410.12232/) (2024)
- [Enhancing Lifelong Multi-Agent Path-finding by Using Artificial Potential Fields](https://mlsanity.com/paper/2505.22753/) (2025)
- [Learning-Based Motion Planning for Dynamic Environments: From Foundational Algorithms to Emerging Paradigms](https://mlsanity.com/paper/2608.00625/) (2026)

## Abstract (arXiv)

This paper introduces a hybrid algorithm of deep reinforcement learning (RL) and Force-based motion planning (FMP) to solve distributed motion planning problem in dense and dynamic environments. Individually, RL and FMP algorithms each have their own limitations. FMP is not able to produce time-optimal paths and existing RL solutions are not able to produce collision-free paths in dense environments. Therefore, we first tried improving the performance of recent RL approaches by introducing a new reward function that not only eliminates the requirement of a pre supervised learning (SL) step but also decreases the chance of collision in crowded environments. That improved things, but there were still a lot of failure cases. So, we developed a hybrid approach to leverage the simpler FMP approach in stuck, simple and high-risk cases, and continue using RL for normal cases in which FMP can't produce optimal path. Also, we extend GA3C-CADRL algorithm to 3D environment. Simulation results show that the proposed algorithm outperforms both deep RL and FMP algorithms and produces up to 50% more successful scenarios than deep RL and up to 75% less extra time to reach goal than FMP.