Obstacle Avoidance for UAS in Continuous Action Space Using Deep Reinforcement Learning

• URL: http://arxiv.org/abs/2111.07037v1
• Date: Sat, 13 Nov 2021 04:44:53 GMT
• Title: Obstacle Avoidance for UAS in Continuous Action Space Using Deep Reinforcement Learning
• Authors: Jueming Hu, Xuxi Yang, Weichang Wang, Peng Wei, Lei Ying, Yongming Liu
• Abstract summary: Obstacle avoidance for small unmanned aircraft is vital for the safety of future urban air mobility. We propose a deep reinforcement learning algorithm based on Proximal Policy Optimization (PPO) to guide autonomous UAS to their destinations. Results show that the proposed model can provide accurate and robust guidance and resolve conflict with a success rate of over 99%.
• Score: 9.891207216312937
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Obstacle avoidance for small unmanned aircraft is vital for the safety of future urban air mobility (UAM) and Unmanned Aircraft System (UAS) Traffic Management (UTM). There are many techniques for real-time robust drone guidance, but many of them solve in discretized airspace and control, which would require an additional path smoothing step to provide flexible commands for UAS. To provide a safe and efficient computational guidance of operations for unmanned aircraft, we explore the use of a deep reinforcement learning algorithm based on Proximal Policy Optimization (PPO) to guide autonomous UAS to their destinations while avoiding obstacles through continuous control. The proposed scenario state representation and reward function can map the continuous state space to continuous control for both heading angle and speed. To verify the performance of the proposed learning framework, we conducted numerical experiments with static and moving obstacles. Uncertainties associated with the environments and safety operation bounds are investigated in detail. Results show that the proposed model can provide accurate and robust guidance and resolve conflict with a success rate of over 99%.

Related papers

• Custom Non-Linear Model Predictive Control for Obstacle Avoidance in Indoor and Outdoor Environments [0.0]
  This paper introduces a Non-linear Model Predictive Control (NMPC) framework for the DJI Matrice 100. The framework supports various trajectory types and employs a penalty-based cost function for control accuracy in tight maneuvers.
  arXiv  Detail & Related papers  (2024-10-03T17:50:19Z)
• RACER: Epistemic Risk-Sensitive RL Enables Fast Driving with Fewer Crashes [57.319845580050924]
  We propose a reinforcement learning framework that combines risk-sensitive control with an adaptive action space curriculum. We show that our algorithm is capable of learning high-speed policies for a real-world off-road driving task.
  arXiv  Detail & Related papers  (2024-05-07T23:32:36Z)
• A Safer Vision-based Autonomous Planning System for Quadrotor UAVs with Dynamic Obstacle Trajectory Prediction and Its Application with LLMs [6.747468447244154]
  This paper proposes a vision-based planning system that combines tracking and trajectory prediction of dynamic obstacles to achieve efficient and reliable autonomous flight. We conduct experiments in both simulation and real-world environments, and the results indicate that our approach can successfully detect and avoid obstacles in dynamic environments in real-time.
  arXiv  Detail & Related papers  (2023-11-21T08:09:00Z)
• Safe multi-agent motion planning under uncertainty for drones using filtered reinforcement learning [6.783774261623415]
  We present a tractable motion planner that builds upon the strengths of reinforcement learning and constrained-control-based trajectory planning. The proposed approach yields a safe, real-time implementable, multi-agent motion planner that is simpler to train than methods based solely on learning.
  arXiv  Detail & Related papers  (2023-10-31T18:09:26Z)
• Toward collision-free trajectory for autonomous and pilot-controlled unmanned aerial vehicles [1.018017727755629]
  This study makes greater use of electronic conspicuity (EC) information made available by PilotAware Ltd in developing an advanced collision management methodology. The merits of the DACM methodology have been demonstrated through extensive simulations and real-world field tests in avoiding mid-air collisions.
  arXiv  Detail & Related papers  (2023-09-18T18:24:31Z)
• Evaluation of Safety Constraints in Autonomous Navigation with Deep Reinforcement Learning [62.997667081978825]
  We compare two learnable navigation policies: safe and unsafe. The safe policy takes the constraints into the account, while the other does not. We show that the safe policy is able to generate trajectories with more clearance (distance to the obstacles) and makes less collisions while training without sacrificing the overall performance.
  arXiv  Detail & Related papers  (2023-07-27T01:04:57Z)
• Reinforcement Learning-Based Air Traffic Deconfliction [7.782300855058585]
  This work focuses on automating the horizontal separation of two aircraft and presents the obstacle avoidance problem as a 2D surrogate optimization task. Using Reinforcement Learning (RL), we optimize the avoidance policy and model the dynamics, interactions, and decision-making. The proposed system generates a quick and achievable avoidance trajectory that satisfies the safety requirements.
  arXiv  Detail & Related papers  (2023-01-05T00:37:20Z)
• Evaluating Model-free Reinforcement Learning toward Safety-critical Tasks [70.76757529955577]
  This paper revisits prior work in this scope from the perspective of state-wise safe RL. We propose Unrolling Safety Layer (USL), a joint method that combines safety optimization and safety projection. To facilitate further research in this area, we reproduce related algorithms in a unified pipeline and incorporate them into SafeRL-Kit.
  arXiv  Detail & Related papers  (2022-12-12T06:30:17Z)
• Differentiable Control Barrier Functions for Vision-based End-to-End Autonomous Driving [100.57791628642624]
  We introduce a safety guaranteed learning framework for vision-based end-to-end autonomous driving. We design a learning system equipped with differentiable control barrier functions (dCBFs) that is trained end-to-end by gradient descent.
  arXiv  Detail & Related papers  (2022-03-04T16:14:33Z)
• Transferable Deep Reinforcement Learning Framework for Autonomous Vehicles with Joint Radar-Data Communications [69.24726496448713]
  We propose an intelligent optimization framework based on the Markov Decision Process (MDP) to help the AV make optimal decisions. We then develop an effective learning algorithm leveraging recent advances of deep reinforcement learning techniques to find the optimal policy for the AV. We show that the proposed transferable deep reinforcement learning framework reduces the obstacle miss detection probability by the AV up to 67% compared to other conventional deep reinforcement learning approaches.
  arXiv  Detail & Related papers  (2021-05-28T08:45:37Z)
• Chance-Constrained Trajectory Optimization for Safe Exploration and Learning of Nonlinear Systems [81.7983463275447]
  Learning-based control algorithms require data collection with abundant supervision for training. We present a new approach for optimal motion planning with safe exploration that integrates chance-constrained optimal control with dynamics learning and feedback control.
  arXiv  Detail & Related papers  (2020-05-09T05:57:43Z)

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.