# Collision Avoidance for Multiple UAVs in Unknown Scenarios with Causal Representation Disentanglement

arXiv: https://arxiv.org/abs/2407.04064 · HTML: https://mlsanity.com/paper/2407.04064/

## 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 20 of its 43 references that are in the map.
- First posted on arXiv 4 Jul 2024.

## 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, 20 of 20)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Deep Transfer Learning with Joint Adaptation Networks](https://mlsanity.com/paper/1605.06636/) (2016)
- [AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles](https://mlsanity.com/paper/1705.05065/) (2017)
- [Learning Invariant Representations for Reinforcement Learning without Reconstruction](https://mlsanity.com/paper/2006.10742/) (2020)
- [A Fourier-based Framework for Domain Generalization](https://mlsanity.com/paper/2105.11120/) (2021)
- [Causality Inspired Representation Learning for Domain Generalization](https://mlsanity.com/paper/2203.14237/) (2022)
- [From Variational to Deterministic Autoencoders](https://mlsanity.com/paper/1903.12436/) (2019)
- [Domain Agnostic Learning with Disentangled Representations](https://mlsanity.com/paper/1904.12347/) (2019)
- [Invariant Causal Prediction for Block MDPs](https://mlsanity.com/paper/2003.06016/) (2020)
- [Observational Overfitting in Reinforcement Learning](https://mlsanity.com/paper/1912.02975/) (2019)
- [A Unified Feature Disentangler for Multi-Domain Image Translation and Manipulation](https://mlsanity.com/paper/1809.01361/) (2018)
- [Learning Disentangled Semantic Representation for Domain Adaptation](https://mlsanity.com/paper/2012.11807/) (2020)
- [Subspace Identification for Multi-Source Domain Adaptation](https://mlsanity.com/paper/2310.04723/) (2023)
- [VOILA: Visual-Observation-Only Imitation Learning for Autonomous Navigation](https://mlsanity.com/paper/2105.09371/) (2021)
- [Trajectory Generation for Multiagent Point-To-Point Transitions via Distributed Model Predictive Control](https://mlsanity.com/paper/1809.04230/) (2018)
- [Distributed Multi-agent Navigation Based on Reciprocal Collision Avoidance and Locally Confined Multi-agent Path Finding](https://mlsanity.com/paper/2107.00246/) (2021)
- [Vision-based Distributed Multi-UAV Collision Avoidance via Deep Reinforcement Learning for Navigation](https://mlsanity.com/paper/2203.02650/) (2022)
- [VG-Swarm: A Vision-based Gene Regulation Network for UAVs Swarm Behavior Emergence](https://mlsanity.com/paper/2206.08669/) (2022)
- [DCAD: Decentralized Collision Avoidance with Dynamics Constraints for Agile Quadrotor Swarms](https://mlsanity.com/paper/1909.03961/) (2019)

## Abstract (arXiv)

Deep reinforcement learning (DRL) has achieved remarkable progress in online path planning tasks for multi-UAV systems. However, existing DRL-based methods often suffer from performance degradation when tackling unseen scenarios, since the non-causal factors in visual representations adversely affect policy learning. To address this issue, we propose a novel representation learning approach, ie, causal representation disentanglement, which can identify the causal and non-causal factors in representations. After that, we only pass causal factors for subsequent policy learning and thus explicitly eliminate the influence of non-causal factors, which effectively improves the generalization ability of DRL models. Experimental results show that our proposed method can achieve robust navigation performance and effective collision avoidance especially in unseen scenarios, which significantly outperforms existing SOTA algorithms.