Deep Reinforcement Learning-Based Approach for a Single Vehicle Persistent Surveillance Problem with Fuel Constraints

This article presents a deep reinforcement learning-based approach to tackle a persistent surveillance mission requiring a single unmanned aerial vehicle initially stationed at a depot with fuel or time-of-flight constraints to repeatedly visit a set of targets with equal priority. Owing to the vehicle's fuel or time-of-flight constraints, the vehicle must be regularly refueled, or its battery must be recharged at the depot. The objective of the problem is to determine an optimal sequence of visits to the targets that minimizes the maximum time elapsed between successive visits to any target while ensuring that the vehicle never runs out of fuel or charge. We present a deep reinforcement learning algorithm to solve this problem and present the results of numerical experiments that corroborate the effectiveness of this approach in comparison with common-sense greedy heuristics.

Off-Road LiDAR Intensity Based Semantic Segmentation

LiDAR is used in autonomous driving to provide 3D spatial information and enable accurate perception in off-road environments, aiding in obstacle detection, mapping, and path planning. Learning-based LiDAR semantic segmentation utilizes machine learning techniques to automatically classify objects and regions in LiDAR point clouds. Learning-based models struggle in off-road environments due to the presence of diverse objects with varying colors, textures, and undefined boundaries, which can lead to difficulties in accurately classifying and segmenting objects using traditional geometric-based features. In this paper, we address this problem by harnessing the LiDAR intensity parameter to enhance object segmentation in off-road environments. Our approach was evaluated in the RELLIS-3D data set and yielded promising results as a preliminary analysis with improved mIoU for classes "puddle" and "grass" compared to more complex deep learning-based benchmarks. The methodology was evaluated for compatibility across both Velodyne and Ouster LiDAR systems, assuring its cross-platform applicability. This analysis advocates for the incorporation of calibrated intensity as a supplementary input, aiming to enhance the prediction accuracy of learning based semantic segmentation frameworks. https://github.com/MOONLABIISERB/lidar-intensity-predictor/tree/main

A COLREGs-Compliant Conflict Resolution Strategy for Autonomous Surface Vehicles

This paper presents a novel conflict resolution strategy for autonomous surface vehicles (ASVs) to safely navigate and avoid collisions in a multi-vessel environment at sea. Collisions between two or more marine vessels must be avoided by following the International Regulations for Preventing Collisions at Sea (COLREGs). We propose strategy a two-phase strategy called as COLREGs Compliant Conflict-Resolving (COMCORE) strategy, that generates collision-free trajectories for ASVs while complying with COLREGs. In phase-1, a shortest path for each agent is determined, while in phase-2 conflicts are detected and resolved by modifying the path in compliance with COLREGs. COMCORE solution optimises vessel trajectories for lower costs while also providing a safe and collision-free plan for each vessel. Simulation results are presented to show the applicability of COMCORE for larger number agents with very low computational requirement and hence scalable. Further, we experimentally demonstrate COMCORE for two ASVs in a lake to show its ability to determine solution and implementation capability in the real-world.

UAV Target Tracking in Urban Environments Using Deep Reinforcement Learning

Persistent target tracking in urban environments using UAV is a difficult task due to the limited field of view, visibility obstruction from obstacles and uncertain target motion. The vehicle needs to plan intelligently in 3D such that the target visibility is maximized. In this paper, we introduce Target Following DQN (TF-DQN), a deep reinforcement learning technique based on Deep Q-Networks with a curriculum training framework for the UAV to persistently track the target in the presence of obstacles and target motion uncertainty. The algorithm is evaluated through several simulation experiments qualitatively as well as quantitatively. The results show that the UAV tracks the target persistently in diverse environments while avoiding obstacles on the trained environments as well as on unseen environments.