SCShaofeng Chen

Shaofeng Chen

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Shaofeng Chen has a total of 23 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Real-Time Neural Model Predictive Control for Quadrotors via Input-Convex Temporal Convolutional Networks

    by Shaofeng Chen, Kejun Wen, Tao Wang, Pengfei Li

    Accurate dynamics models are essential for improving the tracking performance of model predictive control (MPC) for unmanned aerial vehicles (UAV). However, UAV dynamics are highly nonlinear, strongly coupled, and affected by aerodynamic effects with temporal dependence, which are difficult to capture using nominal rigid-body models alone. For this reason, temporal neural networks (TCNs) have been widely used to learn residual dynamics. Nevertheless, repeated evaluation of network outputs and sensitivities during online optimization incurs substantial computational overhead, hindering real-time implementation. Moreover, integrating temporal residual models into real-time MPC requires causally consistent feature histories at future shooting nodes and efficient horizonwise differentiation. To address these issues, this paper proposes a real-time neural MPC framework that integrates an input-convex TCN residual model, history-conditionedbatched local linearization, and real-time iteration sequential quadratic programming (RTI-SQP).The proposed input-convex temporal convolutional network (IC-TCN) employs causal dilated convolutions and sign-symmetric feature lifting to represent history-dependent residuals in linear andangular accelerations. Under the stated nonnegative-weight and structural constraints, each network output is convex with respect to the complete normalized and lifted causal feature history,which provides a structured residual model for online optimization. Furthermore, to reduce repeated neural-network evaluations over the prediction horizon, the history-conditioned networkoutputs and their current-node first-order sensitivities along the warm-start prediction trajectoryare computed in parallel on a GPU at each sampling instant. The resulting local affine models arethen passed to the RTI-SQP solver, thereby avoiding repeated evaluation of the complete temporalnetwork during the feedback phase and effectively decoupling neural-model computation from online optimization. Simulations with aerodynamic model mismatch and external-force disturbancesshow that, in the tested high-speed scenarios, IC-TCN achieves lower tracking errors than a standard TCN. In addition, on the reported desktop CPUGPU platform, the IC-TCN reduces thedata-driven preparation latency by 39.88% relative to the larger standard TCN.

  • An improved LIO-SAM algorithm by integrating image information for dynamic and unstructured environments

    by Xinyu Meng, Xi Chen, Shaofeng Chen, Yongfeng Fang, Hao Fan, Jiyu Luo, Yuhan Wu, Bingyu Sun

    Simultaneous localization and mapping (SLAM) is the process of estimating the trajectory of a mobile sensor carrier and creating a representation of its surroundings. Traditional SLAM algorithms are based on ‘static world assumption’ and simplify the problem by filtering out moving objects or tracking them separately in complex dynamic environments. However, this strong assumption restricts the application of SLAM algorithms on highly dynamic and unstructured environments. In order to resolve above problem, this paper propose an improved object-aware dynamic SLAM system by integrating image information, i.e. semantic and velocity information. Firstly, we adopt deep learning method to detect both the 2D and 3D bounding boxes of objects in the environment. This information is then used to perform multi-view, multi-dimensional bundle optimization to jointly refine the poses of camera, object, and point. Secondly, 2D detection results from image and 3D detection results from lidar are integrated by the joint probabilistic data association data association algorithm to facilitate object-level data association. We also calculate 2D and 3D motion velocity and this information is used to constraint the motion of the object. Finally, we perform comprehensive experiments on different datasets, including NCLT, M2DGR, and KITTI to prove the performance of the proposed method.


  • Graph Convolutional Flocking Control for Unmanned Aerial Vehicles With Packet Dropouts

    by Shaofeng Chen, Yu Kang, Jian Di, Yang Cao

    Flocking control of unmanned aerial vehicles (UAVs) plays a vital role in numerous applications with its adaptability, decentralization, and self-organization. Despite advances, the control performance of present approaches will deteriorate in practical applications due to the disregard of the strong coupling of the complexity of the UAVs (e.g., nonlinearity and strong coupling), agent interaction, and network quality (e.g., time delay and packet dropouts). To address this problem, we propose a novel graph convolutional flocking strategy for nonlinear UAV systems in the event of stochastic packet dropouts over the communication network. Different from the existing methods that only rely on a nominal model, this article formulates the flocking control problem from the perspective of an underlying graph, and exploits the graph convolution to generate a contextualized representation of the spatiotemporal state-control space. A predictive model of packet dropouts is generated with the state-control sequences in the learned representation space. Consequently, a graph convolutional flocking controller including a packet dropout predictive compensation module is proposed. The stability of the closed-loop system is verified by Lyapunov theory. Simulation and physical-world experimental studies for flocking control of a multiquadcopter system are performed to verify the effectiveness of our proposed strategy.


  • A Cooperative-Competitive Strategy for Autonomous Multidrone Racing

    by Jian Di, Shaofeng Chen, Pengfei Li, Xinghu Wang, Haibo Ji, Yu Kang

    Autonomous multidrone racing is extremely challenging due to rich agent interactions and cluttered environments. Although there has been some progress, existing approaches often do not properly consider cooperative behavior among drones and are computationally expensive, deteriorating the racing performance. To address these issues, we propose a novel cooperative-competitive strategy based on the leader-wingman framework for autonomous multidrone racing. For the leader, a game-theoretic method is designed to compete against the opponent. For the wingman, a novel line of sight-based cooperative method is proposed to support the leader by blocking the opponent. As a result, the win rate can be improved even when the opponent has a significant speed advantage. Furthermore, our strategy has a lower computational cost than the existing game-based strategies. Finally, we verify our strategy by extensive comparison to the state-of-the-art strategy in simulation and in the physical world.


  • Convex Temporal Convolutional Network-Based Distributed Cooperative Learning Control for Multiagent Systems

    by Shaofeng Chen, Yu Kang, Jian Di, Pengfei Li, Yang Cao

    Due to its great efficiency, scalability, and inclusivity, distributed cooperative learning control has gotten a lot of attention. For complex uncertain multiagent systems, it is challenging to model the uncertainties and exploit the cooperative learning ability of the systems. To address these issues, we proposed a novel convex temporal convolutional network-based distributed cooperative learning control for uncertain discrete-time nonlinear multiagent systems. A new concept of using a convex temporal convolutional network (CTCNet) is proposed for estimating the uncertain agent dynamics in a cooperative way. Unlike previous methods that require adjustment of network weights for different control tasks, the proposed CTCNet can map the high-dimensional input-output space into a deep space spanned by basis features that represent the inherent properties of the system, so it has good robustness for different tasks. Consequently, to improve the control performance, a CTCNet-based distributed cooperative learning control method that shares learned knowledge through the communication topology among adaptive laws of CTCNet is proposed. Furthermore, the asymptotic convergence of system tracking errors to an arbitrarily small neighborhood of the origin is strictly proved. Finally, the simulation results are given to illustrate that our suggested method has higher control accuracy, stronger robustness, and anti-interference ability than the existing methods.


  • Deep Feature Representation Based Imitation Learning for Autonomous Helicopter Aerobatics

    by Shaofeng Chen, Yang Cao, Yu Kang, Pengfei Li, Bingyu Sun

    The drastic changes in flight parameters during aerobatics and the high instability of the system make the control of autonomous aerobatics unusually difficult. In this paper, we propose a deep feature representation based imitation learning method for autonomous aerobatics, which leverages expert demonstrations to efficiently learn the mapping of high-dimensional flight observations onto continuous actions (pitch, tail, and thrust). Different from the existing methods, our proposed method requires neither trajectory specification and alignment nor any assumptions and processing of system uncertainties, so it can greatly simplify the controller solution steps and reduce the computational burden. Particularly, our method uses the proposed deep feature representation network (DFR-network) to directly map the experts’ demonstration trajectory to a deep representation space spanned by a set of learned subspaces which represent the motion patterns with the same statistical property among demonstration trajectories. Various aerobatic maneuvers can be encoded in the deep representation space through a simple combination of embedding features. Accordingly, the proposed method can perform arbitrary aerobatic maneuvers by observing a limit set of expert demonstrations. The effectiveness of the deep feature representation based imitation learning method is verified on the real-world flight data. Experiments show that compared with the existing methods, our proposed method has higher control accuracy, stronger robustness and anti-interference ability.