Siyuan Wu

Publications

1. 

   Decentralized Multi-Agent Trajectory Planning in Dynamic Environments with Occupancy Prediction

   Siyuan Wu , Gang Chen , Moji Shi , and Javier Alonso-Mora

   Accepted by the 2024 IEEE International Conference on Robotics and Automation (ICRA), Mar 2023

   Abs Code

   This paper proposes a decentralized multi-agent trajectory planning framework based on an occupancy prediction map to address the challenge of autonomous navigation of multiple micro aerial vehicles (MAVs) in dynamic environments. The occupancy prediction map, which forecasts the occupancy status of dynamic and static obstacles in the near future simultaneously, is a promising solution to represent dynamic environments. By using the occupancy prediction map, we avoid segmenting moving obstacles from the environment and simplify the planning problem into multi-time-step planning and propose a decentralized multi-agent planning method. The method extends the kinodynamic A* and the corridor-constrained trajectory optimization algorithm to efficiently tackle static and dynamic obstacles with arbitrary shapes. Collision avoidance between agents is integrated by sharing planned trajectories and projecting them onto the occupancy prediction map. We validate the proposed method in obstacle-dense dynamic environments with different numbers and shapes of static and dynamic obstacles. Simulation results show our methods achieve 47.1% less failure rate and 14.1% less flight time in the dynamic environment with obstacles of different shapes compared to the state-of-the-art method.

2. 

   RAST: Risk-Aware Spatio-Temporal Safety Corridors for MAV Navigation in Dynamic Uncertain Environments

   Gang Chen , Siyuan Wu , Moji Shi , Wei Dong , Hai Zhu , and Javier Alonso-Mora

   IEEE Robotics and Automation Letters (RA-L), Nov 2022

   Abs HTML PDF Code

   Autonomous navigation of Micro Aerial Vehicles (MAVs) in dynamic and unknown environments is a complex and challenging task. Current works rely on assumptions to solve the problem. The MAV’s pose is precisely known, the dynamic obstacles can be explicitly segmented from static ones, their number is known and fixed, or they can be modeled with given shapes. In this paper, we present a method for MAV navigation in dynamic uncertain environments without making any of these assumptions. The method employs a particlebased dynamic map to represent the local environment and predicts it to the near future. Collision risk is defined based on the predicted maps and a series of risk-aware spatio-temporal (RAST) safety corridors are constructed, which are finally used to optimize a dynamically-feasible collision-free trajectory for the MAV. We compared our method with several state-of-the-art works in 9600 simulation tests in Gazebo with the physical engine enabled. The results show that our method has the highest success rate at different uncertainty levels. Finally, we validated the proposed method in real experiments.

3. 

   FAST-Dynamic-Vision: Detection and Tracking Dynamic Objects with Event and Depth Sensing

   Botao He , Haojia Li , Siyuan Wu , Dong Wang , Zhiwei Zhang , Qianli Dong , Chao Xu , and Fei Gao

   In 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Sep 2021

   Abs arXiv HTML PDF Code

   The development of aerial autonomy has enabled aerial robots to fly agilely in complex environments. However, dodging fast-moving objects in flight remains a challenge, limiting the further application of unmanned aerial vehicles (UAVs). The bottleneck of solving this problem is the accurate perception of rapid dynamic objects. Recently, event cameras have shown great potential in solving this problem. This paper presents a complete perception system including ego-motion compensation, object detection, and trajectory prediction for fast-moving dynamic objects with low latency and high precision. Firstly, we propose an accurate ego-motion compensation algorithm by considering both rotational and translational motion for more robust object detection. Then, for dynamic object detection, an event camera-based efficient regression algorithm is designed. Finally, we propose an optimizationbased approach that asynchronously fuses event and depth cameras for trajectory prediction. Extensive real-world experiments and benchmarks are performed to validate our framework. Moreover, our code will be released to benefit related researches.