Multi-Robot Hybrid Coverage Path Planning for 3D Reconstruction of Large Structures

Abstract

Coverage Path Planning (CPP) is an essential capability for autonomous robots operating in various critical applications such as fire fighting, and inspection. Performing autonomous coverage using a single robot system consumes time and energy. In particular, 3D large structures might contain some complex and occluded areas that shall be scanned rapidly in certain application domains. In this paper, a new Hybrid Coverage Path Planning (HCPP) approach is proposed to explore and cover unknown 3D large structures using a decentralized multi-robot system. The HCPP approach combines a guided Next Best View (NBV) approach with a developed Long Short Term Memory (LSTM) waypoint prediction approach to decrease the CPP exploration time at each iteration and simultaneously achieve high coverage. The hybrid approach is the new ML paradigm which fosters intelligence by balancing between data efficiency and generality allowing the exchange of some CPP parts with a learned model. The HCPP uses a stateful LSTM network architecture which is trained based on collected paths that cover different 3D structures to predict the next viewpoint. This architecture captures the dynamic dependencies of adjacent viewpoints in the long term sequences like the coverage paths. The HCPP switches between these methods triggered by either the number of iterations or an entropy threshold. In the decentralized multi-robot system, the proposed HCPP is embedded in each robot where each one of them shares its global 3D map ensuring robustness. The results performed in a realistic Gazebo robotic simulator confirmed the advantage of the proposed HCPP approach by achieving high coverage on different 3D unknown structures in a shorter time compared to conventional NBV.

Improving SLAM Techniques with Integrated Multi-Sensor Fusion for 3D Reconstruction

“…In the domain of SLAM with multi-sensor fusion, the significance of 3D reconstruction is paramount, serving as a crucial component in environmental perception and comprehension for autonomous systems. By meticulously crafting precise three-dimensional models of the surrounding environment, 3D reconstruction significantly augments the capabilities of robots and autonomous vehicles in executing tasks such as path planning, navigation, and obstacle avoidance [43]. Moreover, the seamless integration of multi-sensor fusion techniques with SLAM not only bolsters the accuracy and robustness of 3D reconstruction, but also elevates the overall performance of SLAM systems by imparting richer and more intricate environmental information [44].…”

Research on multi-robot collaborative operation in logistics and warehousing using A3C optimized YOLOv5-PPO model

“…With the development of deep learning, models such as Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM) have become emerging choices for time series prediction. These deep learning models are better able to capture nonlinear relationships and long-term dependencies in time series, and are suitable for complex and non-stationary time series data (Almadhoun et al, 2021 ). In the field of logistics and warehousing robots, these models have been successfully used in tasks such as predicting the flow of goods and predicting demand changes.…”

UPPLIED: UAV Path Planning for Inspection through Demonstration

“…Samplingbased CPP methods generate redundant viewpoints around the structure and optimize these viewpoints to achieve complete coverage [8,9]. Multi-UAV-based CPP methods have also been developed to reduce the inspection time and cover larger areas [10,18]. However, the goal of all CPP methods proposed in the literature is to achieve complete coverage, which may not be desired in all scenarios.…”