Learning Multi-Pursuit Evasion for Safe Targeted Navigation of Drones
- URL: http://arxiv.org/abs/2304.03443v2
- Date: Wed, 21 Feb 2024 02:34:13 GMT
- Title: Learning Multi-Pursuit Evasion for Safe Targeted Navigation of Drones
- Authors: Jiaping Xiao and Mir Feroskhan
- Abstract summary: This paper proposes a novel approach, asynchronous multi-stage deep reinforcement learning (AMS-DRL), to train adversarial neural networks.
AMS-DRL evolves adversarial agents in a pursuit-evasion game where the pursuers and the evader are asynchronously trained in a bipartite graph way.
We evaluate our method in extensive simulations and show that it outperforms baselines with higher navigation success rates.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Safe navigation of drones in the presence of adversarial physical attacks
from multiple pursuers is a challenging task. This paper proposes a novel
approach, asynchronous multi-stage deep reinforcement learning (AMS-DRL), to
train adversarial neural networks that can learn from the actions of multiple
evolved pursuers and adapt quickly to their behavior, enabling the drone to
avoid attacks and reach its target. Specifically, AMS-DRL evolves adversarial
agents in a pursuit-evasion game where the pursuers and the evader are
asynchronously trained in a bipartite graph way during multiple stages. Our
approach guarantees convergence by ensuring Nash equilibrium among agents from
the game-theory analysis. We evaluate our method in extensive simulations and
show that it outperforms baselines with higher navigation success rates. We
also analyze how parameters such as the relative maximum speed affect
navigation performance. Furthermore, we have conducted physical experiments and
validated the effectiveness of the trained policies in real-time flights. A
success rate heatmap is introduced to elucidate how spatial geometry influences
navigation outcomes. Project website:
https://github.com/NTU-ICG/AMS-DRL-for-Pursuit-Evasion.
Related papers
- Efficient Adversarial Training in LLMs with Continuous Attacks [99.5882845458567]
Large language models (LLMs) are vulnerable to adversarial attacks that can bypass their safety guardrails.
We propose a fast adversarial training algorithm (C-AdvUL) composed of two losses.
C-AdvIPO is an adversarial variant of IPO that does not require utility data for adversarially robust alignment.
arXiv Detail & Related papers (2024-05-24T14:20:09Z) - Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents [49.85633804913796]
We present an exploration-based trajectory optimization approach, referred to as ETO.
This learning method is designed to enhance the performance of open LLM agents.
Our experiments on three complex tasks demonstrate that ETO consistently surpasses baseline performance by a large margin.
arXiv Detail & Related papers (2024-03-04T21:50:29Z) - A Dual Curriculum Learning Framework for Multi-UAV Pursuit-Evasion in Diverse Environments [15.959963737956848]
This paper addresses multi-UAV pursuit-evasion, where a group of drones cooperate to capture a fast evader in a confined environment with obstacles.
Existing algorithms, which simplify the pursuit-evasion problem, often lack expressive coordination strategies and struggle to capture the evader in extreme scenarios.
We introduce a dual curriculum learning framework, named DualCL, which addresses multi-UAV pursuit-evasion in diverse environments and demonstrates zero-shot transfer ability to unseen scenarios.
arXiv Detail & Related papers (2023-12-19T15:39:09Z) - Rethinking Closed-loop Training for Autonomous Driving [82.61418945804544]
We present the first empirical study which analyzes the effects of different training benchmark designs on the success of learning agents.
We propose trajectory value learning (TRAVL), an RL-based driving agent that performs planning with multistep look-ahead.
Our experiments show that TRAVL can learn much faster and produce safer maneuvers compared to all the baselines.
arXiv Detail & Related papers (2023-06-27T17:58:39Z) - Ada-NAV: Adaptive Trajectory Length-Based Sample Efficient Policy Learning for Robotic Navigation [72.24964965882783]
Trajectory length plays a pivotal role in the training process of reinforcement learning algorithms.
We introduce Ada-NAV, a novel adaptive trajectory length scheme to enhance the training sample efficiency of RL algorithms.
We demonstrate through simulated and real-world robotic experiments that Ada-NAV outperforms conventional methods.
arXiv Detail & Related papers (2023-06-09T18:45:15Z) - Deep Reinforcement Learning-Based Mapless Crowd Navigation with
Perceived Risk of the Moving Crowd for Mobile Robots [0.0]
Current state-of-the-art crowd navigation approaches are mainly deep reinforcement learning (DRL)-based.
We propose a method that includes a Collision Probability (CP) in the observation space to give the robot a sense of the level of danger of the moving crowd.
arXiv Detail & Related papers (2023-04-07T11:29:59Z) - Collaborative Target Search with a Visual Drone Swarm: An Adaptive
Curriculum Embedded Multistage Reinforcement Learning Approach [0.0]
We propose a novel data-efficient deep reinforcement learning (DRL) approach called adaptive curriculum embedded multistage learning (ACEMSL)
We decompose the collaborative target search task into several subtasks including individual obstacle avoidance, target search, and inter-agent collaboration, and progressively train the agents with multistage learning.
We deploy the trained model over a real visual drone swarm and perform CTS operations without fine-tuning.
arXiv Detail & Related papers (2022-04-26T09:32:22Z) - Benchmarking Safe Deep Reinforcement Learning in Aquatic Navigation [78.17108227614928]
We propose a benchmark environment for Safe Reinforcement Learning focusing on aquatic navigation.
We consider a value-based and policy-gradient Deep Reinforcement Learning (DRL)
We also propose a verification strategy that checks the behavior of the trained models over a set of desired properties.
arXiv Detail & Related papers (2021-12-16T16:53:56Z) - Decentralized Reinforcement Learning for Multi-Target Search and
Detection by a Team of Drones [12.055303570215335]
Targets search and detection encompasses a variety of decision problems such as coverage, surveillance, search, observing and pursuit-evasion.
We develop a multi-agent deep reinforcement learning (MADRL) method to coordinate a group of aerial vehicles (drones) for the purpose of locating a set of static targets in an unknown area.
arXiv Detail & Related papers (2021-03-17T09:04:47Z) - Robust Deep Reinforcement Learning through Adversarial Loss [74.20501663956604]
Recent studies have shown that deep reinforcement learning agents are vulnerable to small adversarial perturbations on the agent's inputs.
We propose RADIAL-RL, a principled framework to train reinforcement learning agents with improved robustness against adversarial attacks.
arXiv Detail & Related papers (2020-08-05T07:49:42Z) - COLREG-Compliant Collision Avoidance for Unmanned Surface Vehicle using
Deep Reinforcement Learning [0.0]
Path Following and Collision Avoidance, be it for unmanned surface vessels or other autonomous vehicles, are two fundamental guidance problems in robotics.
In this article, we explore the potential of Proximal Policy Optimization (PPO), a DRL algorithm with demonstrated state-of-the-art performance on Continuous Control tasks.
Based on high-fidelity elevation and AIS tracking data from the Trondheim Fjord, an inlet of the Norwegian sea, we evaluate the trained agent's performance in challenging, dynamic real-world scenarios.
arXiv Detail & Related papers (2020-06-16T22:05:58Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.