Publications
Journal Papers
2023
- RA-LSMART: Self-Morphing Adaptive Replanning TreeZongyuan Shen, James P Wilson, Shalabh Gupta, and Ryan HarveyIEEE Robotics and Automation Letters, Nov 2023
This paper presents an algorithm, called Self-Morphing Adaptive Replanning Tree (SMART), that facilitates fast replanning in dynamic environments. SMART performs risk-based tree-pruning if the current path is obstructed by nearby moving obstacle(s), resulting in multiple disjoint subtrees. Then, for speedy recovery, it exploits these subtrees and performs informed tree-repair at hot-spots that lie at the intersection of subtrees to find a new path. The performance of SMART is comparatively evaluated with eight existing algorithms through extensive simulations. Two scenarios are considered with: 1) dynamic obstacles and 2) both static and dynamic obstacles. The results show that SMART yields significant improvements in replanning time, success rate, and travel time. Finally, the performance of SMART is validated by a real laboratory experiment.
2022
- RA-LCT-CPP: Coverage Path Planning for 3D Terrain Reconstruction Using Dynamic Coverage TreesZongyuan Shen, Junnan Song, Khushboo Mittal, and Shalabh GuptaIEEE Robotics and Automation Letters, Jan 2022
This paper addresses the 3D coverage path planning (CPP) problem for terrain reconstruction of unknown obstacle-rich environments. Due to sensing limitations, the proposed method, called CT-CPP, performs layered scanning of the 3D region to collect terrain data, where the traveling sequence is optimized using the concept of a coverage tree (CT) with a TSP-inspired tree traversal strategy. The CT-CPP method is validated on a high-fidelity underwater simulator and the results are compared to an existing terrain following CPP method. The results show that CT-CPP yields significant reduction in trajectory length, energy consumption, and reconstruction error.
- JAMPMulti-objective optimization for cost-efficient and resilient machining under tool wearJames P Wilson, Zongyuan Shen, Utsav Awasthi, George M Bollas, and Shalabh GuptaJournal of Advanced Manufacturing and Processing, Jul 2022
With the onset and rapid growth of smart manufacturing, there is a constant increase in the demand for automation technologies to enhance productivity while providing uninterrupted, cost-efficient, and resilient machining. Traditional manufacturing systems, however, suffer from several losses due to machine faults and degradation. Specifically, tool wear directly impacts the precision and quality of the milled parts, which causes an increase in the scrap production. Hence, more attempts are required to meet the desired quota of successful parts, which in turn results in wasted material, longer delays, further tool degradation, and higher energy, machining, and labor costs. As such, this paper develops a multi-objective optimization framework to generate the optimal control set points (e.g., feed rate and width of cut) that minimize the total cost of machining operations resulting from multiple contradictory cost functions (e.g., material, energy, tardiness, machining, labor, and tool) in the presence of tool wear. Notably, we estimate the total expected cost in dollars, which provides automatic and intuitive weighting in this multi-objective formulation. The optimization framework is tested on a high-fidelity face milling model that has been validated on real data from industry. Results show significant dollar savings of up to 15% as compared to the default control scheme.
Conference Papers
2025
2021
- OceansCPPNet: A Coverage Path Planning NetworkZongyuan Shen, Palash Agrawal, James P. Wilson, Ryan Harvey, and Shalabh GuptaIn Proc. OCEANS’21 MTS/IEEE, Sep 2021
This paper presents a deep-learning based CPP algorithm, called Coverage Path Planning Network (CPPNet). CPPNet is built using a convolutional neural network (CNN) whose input is a graph-based representation of the occupancy grid map while its output is an edge probability heat graph, where the value of each edge is the probability of belonging to the optimal TSP tour. Finally, a greedy search is used to select the final optimized tour. CPPNet is trained and comparatively evaluated against the TSP tour. It is shown that CPPNet provides near-optimal solutions while requiring significantly less computational time, thus enabling real-time coverage path planning in partially unknown and dynamic environments.
- OceansA Non-uniform Sampling Approach for Fast and Efficient Path PlanningJames P. Wilson, Zongyuan Shen, and Shalabh GuptaIn Proc. OCEANS’21 MTS/IEEE, Sep 2021
In this paper, we develop a non-uniform sampling approach for fast and efficient path planning of autonomous vehicles. The approach uses a novel non-uniform partitioning scheme that divides the area into obstacle-free convex cells. The partitioning results in large cells in obstacle-free areas and small cells in obstacle-dense areas. Subsequently, the boundaries of these cells are used for sampling; thus significantly reducing the burden of uniform sampling. When compared with a standard uniform sampler, this smart sampler significantly 1) reduces the size of the sampling space while providing completeness and optimality guarantee, 2) provides sparse sampling in obstacle-free regions and dense sampling in obstacle-rich regions to facilitate faster exploration, and 3) eliminates the need for expensive collision-checking with obstacles due to the convexity of the cells. This sampling framework is incorporated into the RRT* path planner. The results show that RRT* with the non-uniform sampler gives a significantly better convergence rate and smaller memory footprint as compared to RRT* with a uniform sampler.
2020
- Oceansɛ*+: An Online Coverage Path Planning Algorithm for Energy-constrained Autonomous VehiclesZongyuan Shen, James P. Wilson, and Shalabh GuptaIn Proc. OCEANS’20 MTS/IEEE, Oct 2020
This paper presents a novel algorithm, called ε*+, for online coverage path planning of unknown environments using energy-constrained autonomous vehicles. Due to limited battery size, the energy-constrained vehicles have limited duration of operation time. Therefore, while executing a coverage trajectory, the vehicle has to return to the charging station for a recharge before the battery runs out. In this regard, the ε*+ algorithm enables the vehicle to retreat back to the charging station based on the remaining energy which is monitored throughout the coverage process. This is followed by an advance trajectory that takes the vehicle to a near by unexplored waypoint to restart the coverage process, instead of taking it back to the previous left over point of the retreat trajectory; thus reducing the overall coverage time. The proposed ε*+ algorithm is an extension of the ε* algorithm, which utilizes an Exploratory Turing Machine (ETM) as a supervisor to navigate the vehicle with back and forth trajectory for complete coverage. The performance of the ε*+ algorithm is validated on complex scenarios using Player/Stage which is a high-fidelity robotic simulator.
- OceansT*-Lite: A Fast Time-Risk Optimal Motion Planning Algorithm for Multi-Speed Autonomous VehiclesJames P. Wilson, Zongyuan Shen, Shalabh Gupta, and Thomas A. WettergrenIn Proc. OCEANS’20 MTS/IEEE, Oct 2020
In this paper, we develop a new algorithm, called T*-Lite, that enables fast time-risk optimal motion planning for variable-speed autonomous vehicles. The T*-Lite algorithm is a significantly faster version of the previously developed T algorithm. T*-Lite uses the novel time-risk cost function of T*; however, instead of a grid-based approach, it uses an asymptotically optimal sampling-based motion planner. Furthermore, it utilizes the recently developed Generalized Multi-speed Dubins Motion-model (GMDM) for sample-to-sample kinodynamic motion planning. The sample-based approach and GMDM significantly reduce the computational burden of T* while providing reasonable solution quality. The sample points are drawn from a four-dimensional configuration space consisting of two position coordinates plus vehicle heading and speed. Specifically, T*-Lite enables the motion planner to select the vehicle speed and direction based on its proximity to the obstacle to generate faster and safer paths. In this paper, T*-Lite is developed using the RRT* motion planner, but adaptation to other motion planners is straightforward and depends on the needs of the planner.
2019
- OceansAn Online Coverage Path Planning Algorithm for Curvature-Constrained AUVsZongyuan Shen, James P. Wilson, and Shalabh GuptaIn Proc. OCEANS’19 MTS/IEEE, Oct 2019
The paper presents an algorithm for online coverage path planning of unknown environments using curvature-constrained AUVs. Unlike point vehicles, which can make quick maneuvers in any direction towards any goal, curvature-constrained AUVs need significant time to accelerate, decelerate, or turn towards the goal. Therefore, finding a feasible collision-free path to the waypoint in the presence of obstacles is a nontrivial task for curvature-constrained AUVs. In order to overcome this challenge, we develop a new algorithm that dynamically selects the shortest Dubins path from its current state to a neighboring region in a locally optimal manner while providing efficient global coverage. The proposed new algorithm is an extension of our recently developed algorithm called ε*, which utilizes an Exploratory Turing Machine (ETM) as a supervisor to guide the vehicle with adaptive navigation decisions. The performance of the proposed algorithm is validated on a high-fidelity underwater simulator called UWSim, where the collected terrain data is used offline for 3-D reconstruction of the seabed. The simulations show that the proposed algorithm generates feasible and safe coverage paths for curvature-constrained AUVs for accurate reconstruction of the underwater terrain.
2017
- OceansAutonomous 3-D mapping and safe-path planning for underwater terrain reconstruction using multi-level coverage treesZongyuan Shen, Junnan Song, Khushboo Mittal, and Shalabh GuptaIn Proc. OCEANS’17 MTS/IEEE, Sep 2017
This paper presents an autonomous approach of 3-D reconstruction of underwater terrain using multi-level coverage trees. An autonomous underwater vehicle (AUV) equipped with multi-beam sonar sensors, Doppler velocity log (DVL) and inertial measurement unit (IMU) sensors is used to achieve this goal. The underwater 3-D search space is represented by a multi-level coverage tree which is generated online based on the obstacle information collected by the AUV. The nodes of the tree correspond to safe sub-areas for AUV navigation which are identified based on obstacle density in neighborhood of free cells. Standard tree traversal strategies like depth-first-search (DFS) and breath-first-search (BFS) are then used for visiting all the nodes of the tree thus securing complete coverage of the 3-D space. The terrain data collected by the AUV during tree coverage is used offline for the 3-D reconstruction of seabed using alpha shapes algorithm. The performance of this method is validated using a high-fidelity underwater simulator UWSim based on Robot Operating System (ROS). The simulations show that the proposed methodology achieves safe path planning and accurate reconstruction of the 3-D map of the underwater terrain.
2016
- OceansAn autonomous integrated system for 3-D underwater terrain map reconstructionZongyuan Shen, Junnan Song, Khushboo Mittal, and Shalabh GuptaIn Proc. OCEANS’16 MTS/IEEE, Sep 2016
This paper presents a novel integrated approach of creating a 3-D surface map of seabed terrain using an Autonomous Underwater Vehicle (AUV) equipped with various sensors such as multi-beam sonar sensors, DVL, and IMU. The underwater terrain map is useful for various applications like fishery, search and rescue operations, underwater surveillance, mine hunting, etc. The acoustic sensors mounted on the AUV overcome the unfavorable underwater conditions like nonuniform illumination and restricted visibility. In the proposed methodology, the AUV is autonomously navigated using a navigation controller on a flat 2-D surface at a certain depth, to cover an a priori unknown area using an adaptive path planning algorithm. The terrain data is captured by the down-facing multi-beam sonar sensors. The Long Baseline (LBL) localization system and PID controllers are used to drive the AUV to the set-points given by the navigation controller. The collected data is then used offline to construct a 3-D map of seabed using alpha shapes. The performance of this method is tested and validated using a high-fidelity underwater simulator UWSim based on Robot Operating System (ROS). In the simulation runs, the proposed methodology is shown to reconstruct accurate 3-D maps of the seabed.
Thesis
2024
- PhD DissertationMotion Planning in Dynamic and Unknown EnvironmentsZongyuan ShenUniversity of Connecticut, 2024
2017
- Master’s Thesis3-D Coverage Path Planning for Underwater Terrain MappingZongyuan ShenUniversity of Connecticut, 2017
This thesis presents an autonomous approach of 3-D coverage of underwater terrain using multi-level coverage trees. An autonomous underwater vehicle (AUV) equipped with multi-beam sonar sensors, Doppler velocity log (DVL) and inertial measurement unit (IMU) sensors is used to achieve this goal. The underwater 3-D search space is represented by a multi-level coverage tree which is generated online based on the obstacle information collected by the AUV. The nodes of the tree correspond to safe sub-areas for AUV navigation which are identified based on obstacle density in neighborhood of free cells. Standard tree traversal strategies like depth-first-search (DFS) and breath-first-search (BFS) are then used for visiting all the nodes of the tree thus securing complete coverage of the 3-D space. The terrain data collected by the AUV during tree coverage is used offline for the 3-D reconstruction of seabed using alpha shapes algorithm. The performance of this method is validated using a high-fidelity underwater simulator UWSim based on Robot Operating System (ROS). The simulations show that the proposed methodology achieves complete coverage and accurate reconstruction of 3-D underwater terrain.