Tianwei Niu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Tianwei Niu has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Shoukun Wang
School of Automation, Beijing Institute of Technology, Beijing, China
7 shared publications - Junzheng Wang
School of Automation, Beijing Institute of Technology, Beijing, China
5 shared publications - Lin Zhang
School of Automation, Beijing Institute of Technology, Beijing, China
4 shared publications - Runjiao Bao
School of Automation, Beijing Institute of Technology, Beijing, China
3 shared publications - Shengshan Ma
School of Automation, Beijing Institute of Technology, Beijing, China
3 shared publications - Haoyu Yuan
School of Automation, Beijing Institute of Technology, Beijing, China
2 shared publications
Latest Publications
- 30 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (14) , 31692-31706
Terrain-Coupled Hierarchical Optimization for Multirobot Deployment With a Global Reachability–Cost Atlas
Autonomous multi-robot deployment (MRD) aims to determine feasible and task-effective deployment poses for robots to accomplish cooperative missions. When applied to unstructured outdoor environments, MRD must contend with irregular terrain geometry, uneven contact surfaces, and terrain-dependent traversability, challenging purely geometric MRD methods. This work proposes a hierarchical MRD framework that unifies terrain-coupled feasibility modeling and execution-aware optimization into a coherent deployment process. An upper-stage nonlinear programming, constrained by a signed-distance field derived from a multi-layer terrain assessment map (MTAM), enforces strict geometric deployment feasibility and yields high-quality candidate fleet configurations. A lower-stage multi-objective evolutionary optimizer then refines fleet poses using a global reachability-cost atlas (GRCA) that precomputes reachability and minimal traversal cost of each robot to every map cell, enabling constant-time candidate evaluation. Terrain coupling is achieved by embedding terrain-risk layers of the MTAM into the optimization objectives, guiding pose refinement toward stable and traversable regions. Extensive simulations and field trials on vibroseis fleet demonstrate system-level integration within a seismic source excitation pipeline, achieving task-level geometric accuracy, stable terrain contact at deployment poses, and real-time onboard optimization with an average latency below 10 s.
- 30 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (14) , 31692-31706
Terrain-Coupled Hierarchical Optimization for Multirobot Deployment With a Global Reachability–Cost Atlas
Autonomous multi-robot deployment (MRD) aims to determine feasible and task-effective deployment poses for robots to accomplish cooperative missions. When applied to unstructured outdoor environments, MRD must contend with irregular terrain geometry, uneven contact surfaces, and terrain-dependent traversability, challenging purely geometric MRD methods. This work proposes a hierarchical MRD framework that unifies terrain-coupled feasibility modeling and execution-aware optimization into a coherent deployment process. An upper-stage nonlinear programming, constrained by a signed-distance field derived from a multi-layer terrain assessment map (MTAM), enforces strict geometric deployment feasibility and yields high-quality candidate fleet configurations. A lower-stage multi-objective evolutionary optimizer then refines fleet poses using a global reachability-cost atlas (GRCA) that precomputes reachability and minimal traversal cost of each robot to every map cell, enabling constant-time candidate evaluation. Terrain coupling is achieved by embedding terrain-risk layers of the MTAM into the optimization objectives, guiding pose refinement toward stable and traversable regions. Extensive simulations and field trials on vibroseis fleet demonstrate system-level integration within a seismic source excitation pipeline, achieving task-level geometric accuracy, stable terrain contact at deployment poses, and real-time onboard optimization with an average latency below 10 s.
- 9 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 23 (15455955) , 7979-7994
Proprioception-Guided Framework for Terrain Roughness Assessment and Bayesian RRG Planning
Irregular and unpredictable terrains in unstructured environments, including mountains, deserts, rural areas and construction sites, remain a fundamental obstacle to reliable autonomous navigation. The primary difficulty lies in enabling vehicles to accurately understand the risks posed by complex terrains and traverse along flat paths. To address these challenges, this paper presents a terrain-aware path planning framework that couples proprioceptive-sensitive roughness assessment with an improved rapidly-exploring random graph (RRG). From first principles, we design a multi-scale frequency-domain analysis network (MFDAN) that learns terrain roughness from vehicle proprioceptive responses, isolating the frequency bands most responsible for jolts. These bands underpin a terrain roughness map aligned with the vehicle’s dynamic response to the terrain. Building on this map, we introduce a Bayesian learning RRG planner that integrates roughness gradients for high-yield expansion and online Bayesian updating to bias exploration toward safer and more promising directions. The proposed framework is extensively validated in diverse Gazebo simulations and against state-of-the-art baselines, demonstrating significant reductions in jolt level, planning failures, and computation time. Finally, real-world deployment on a 40-ton vibroseis truck in unstructured field environments confirms the practicality and robustness of the framework.
- 9 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 23 (15455955) , 7979-7994
Proprioception-Guided Framework for Terrain Roughness Assessment and Bayesian RRG Planning
Irregular and unpredictable terrains in unstructured environments, including mountains, deserts, rural areas and construction sites, remain a fundamental obstacle to reliable autonomous navigation. The primary difficulty lies in enabling vehicles to accurately understand the risks posed by complex terrains and traverse along flat paths. To address these challenges, this paper presents a terrain-aware path planning framework that couples proprioceptive-sensitive roughness assessment with an improved rapidly-exploring random graph (RRG). From first principles, we design a multi-scale frequency-domain analysis network (MFDAN) that learns terrain roughness from vehicle proprioceptive responses, isolating the frequency bands most responsible for jolts. These bands underpin a terrain roughness map aligned with the vehicle’s dynamic response to the terrain. Building on this map, we introduce a Bayesian learning RRG planner that integrates roughness gradients for high-yield expansion and online Bayesian updating to bias exploration toward safer and more promising directions. The proposed framework is extensively validated in diverse Gazebo simulations and against state-of-the-art baselines, demonstrating significant reductions in jolt level, planning failures, and computation time. Finally, real-world deployment on a 40-ton vibroseis truck in unstructured field environments confirms the practicality and robustness of the framework.
- 31 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. PP (02780046) , 1-11
GMPPO: Guided Model Predictive Path Optimization for Mobile Robots in Obstacle-Constrained Environments
Autonomous navigation of industrial mobile robots in obstacle-constrained environment, such as manufacturing floors, warehouse storage systems, and factory inspection scenarios, poses significant challenges in ensuring path feasibility, safety, and real-time performance. This article proposes a guided model predictive path optimization (GMPPO) framework to address these issues. First, an enhanced convex feasible set algorithm is employed to generate robust initial paths by integrating decoupled dimensionality reduction and a dual-layer fault-tolerant mechanism. Second, based on this reference path, robot geometry, and real-time obstacle information, dynamic safety corridors are constructed to characterize local feasible spaces. Finally, these reference paths and corresponding safety corridors guide a high-fidelity model predictive optimization process, yielding smooth, dynamically feasible, and collision-free trajectories under nonholonomic constraints. Theoretical analysis establishes the resolution completeness and feasibility guarantee of the proposed method. Extensive simulations, real-world robotic experiments, and engineering deployments demonstrate that GMPPO significantly improves planning success rates, trajectory smoothness, and operational safety, while maintaining high computational efficiency and broad applicability.
- 31 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. PP (02780046) , 1-11
GMPPO: Guided Model Predictive Path Optimization for Mobile Robots in Obstacle-Constrained Environments
Autonomous navigation of industrial mobile robots in obstacle-constrained environment, such as manufacturing floors, warehouse storage systems, and factory inspection scenarios, poses significant challenges in ensuring path feasibility, safety, and real-time performance. This article proposes a guided model predictive path optimization (GMPPO) framework to address these issues. First, an enhanced convex feasible set algorithm is employed to generate robust initial paths by integrating decoupled dimensionality reduction and a dual-layer fault-tolerant mechanism. Second, based on this reference path, robot geometry, and real-time obstacle information, dynamic safety corridors are constructed to characterize local feasible spaces. Finally, these reference paths and corresponding safety corridors guide a high-fidelity model predictive optimization process, yielding smooth, dynamically feasible, and collision-free trajectories under nonholonomic constraints. Theoretical analysis establishes the resolution completeness and feasibility guarantee of the proposed method. Extensive simulations, real-world robotic experiments, and engineering deployments demonstrate that GMPPO significantly improves planning success rates, trajectory smoothness, and operational safety, while maintaining high computational efficiency and broad applicability.
- 3 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (4) , 5104-5111
Hierarchical Terrain-Aware Navigation via Bayesian-Guided RRT* and Flat-Corridor CiLQR
Autonomous navigation in unstructured, off-road environments remains a critical challenge due to complex terrain and limited prior knowledge. This letter presents a hierarchical framework to generate paths across locally flat regions and optimize spatio-temporal trajectories under vehicle kinodynamics. The first step employs a terrain-aware RRT* that integrates Bayesian-learning-guided sampling with a directional reachability index, enabling efficient exploration in complex environments while avoiding dead-end traps. The resulting path explicitly accounts for local roughness and slope. The second step applies a constrained iterative linear quadratic regulator (CiLQR) trajectory optimizer that refines the path within a dynamic flat-corridor, where terrain risk is embedded into the optimization. The optimizer enforces vehicle stability constraints and adaptively regulates speed based on terrain risk and curvature, yielding dynamically feasible trajectory. Extensive simulations in off-road scenarios demonstrate that the proposed framework outperforms state-of-the-art methods, producing feasible trajectories with up to 34 % lower vehicle jolt. Furthermore, real-world tests on a 40-ton articulated truck in the Alxa Desert validate the framework's robustness and practical effectiveness.
- 3 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (4) , 5104-5111
Hierarchical Terrain-Aware Navigation via Bayesian-Guided RRT* and Flat-Corridor CiLQR
Autonomous navigation in unstructured, off-road environments remains a critical challenge due to complex terrain and limited prior knowledge. This letter presents a hierarchical framework to generate paths across locally flat regions and optimize spatio-temporal trajectories under vehicle kinodynamics. The first step employs a terrain-aware RRT* that integrates Bayesian-learning-guided sampling with a directional reachability index, enabling efficient exploration in complex environments while avoiding dead-end traps. The resulting path explicitly accounts for local roughness and slope. The second step applies a constrained iterative linear quadratic regulator (CiLQR) trajectory optimizer that refines the path within a dynamic flat-corridor, where terrain risk is embedded into the optimization. The optimizer enforces vehicle stability constraints and adaptively regulates speed based on terrain risk and curvature, yielding dynamically feasible trajectory. Extensive simulations in off-road scenarios demonstrate that the proposed framework outperforms state-of-the-art methods, producing feasible trajectories with up to 34 % lower vehicle jolt. Furthermore, real-world tests on a 40-ton articulated truck in the Alxa Desert validate the framework's robustness and practical effectiveness.
- 26 February 2026
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 37 (11)
Adaptive Speed Planning and Cooperative Formation Operation System for Special-Purpose Vehicles in Field Environments
In complex off-road environments, traditional operations of special-purpose vehicles often suffer from limited terrain perception, restricted speed regulation, and low formation coordination efficiency. This study proposes a systematic framework for autonomous field operations. We first develop a multi-source perception and control architecture that integrates GNSS, LiDAR, vision sensing, and onboard computing into a hierarchical "perception-decision-control" closed loop, enabling both precise single-vehicle operation and coordinated multi-vehicle tasks. To mitigate roll and vibration arising from terrain-speed mismatch, we introduce an adaptive speed-planning method driven by terrain frequency-domain features. In addition, an improved distributed model predictive control (MPC) for cooperative formation operation is designed, leveraging a leader-follower scheme and an articulated-vehicle model to achieve stable formation maneuvering and high-accuracy task execution. The system has been deployed on vibroseis trucks and validated in real-world geological exploration, demonstrating strong robustness and engineering feasibility. Its successful operation at the exploration bases of the China National Petroleum Corporation further confirms its reliability and practical value.
- 26 February 2026
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 37 (11)
Adaptive Speed Planning and Cooperative Formation Operation System for Special-Purpose Vehicles in Field Environments
In complex off-road environments, traditional operations of special-purpose vehicles often suffer from limited terrain perception, restricted speed regulation, and low formation coordination efficiency. This study proposes a systematic framework for autonomous field operations. We first develop a multi-source perception and control architecture that integrates GNSS, LiDAR, vision sensing, and onboard computing into a hierarchical "perception-decision-control" closed loop, enabling both precise single-vehicle operation and coordinated multi-vehicle tasks. To mitigate roll and vibration arising from terrain-speed mismatch, we introduce an adaptive speed-planning method driven by terrain frequency-domain features. In addition, an improved distributed model predictive control (MPC) for cooperative formation operation is designed, leveraging a leader-follower scheme and an articulated-vehicle model to achieve stable formation maneuvering and high-accuracy task execution. The system has been deployed on vibroseis trucks and validated in real-world geological exploration, demonstrating strong robustness and engineering feasibility. Its successful operation at the exploration bases of the China National Petroleum Corporation further confirms its reliability and practical value.
- 25 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 22 (15455955) , 21897-21912
STGN: A Spatio-Temporal Graph Network for Real-Time and Generalizable Trajectory Planning
In dynamic and unstructured environments, mobile robots need to generate safe and efficient trajectories in real time, which poses significant challenges due to the uncertainty of surrounding obstacles. To address this, this article presents a real-time obstacle avoidance trajectory planning method, built upon a spatio-temporal graph network that integrates temporal modeling with graph attention mechanisms. The proposed network captures both temporal dynamics and spatial structural dependencies in dynamic environments by integrating a temporal information module based on long short-term memory (LSTM) and a spatial module based on relational graph attention networks (RGAT). On the whole, the approach follows a two-phase pipeline. In the offline phase, a high-quality trajectory dataset is constructed to represent the heterogeneous state graph of the robot and surrounding obstacles. Then the dataset is used to train the spatio-temporal network, which learns to map environment-state graphs to optimal control commands. In the online phase, the trained network is deployed on the robot to perform real-time perception, decision-making, and control, forming a closed-loop trajectory optimization process. Extensive experiments in both simulated and real-world scenarios demonstrate that the proposed method achieves high-quality trajectory planning, robust obstacle avoidance, and fast generalization under multi-obstacle and sudden disturbance conditions, while maintaining low computational overhead.
- 25 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 22 (15455955) , 21897-21912
STGN: A Spatio-Temporal Graph Network for Real-Time and Generalizable Trajectory Planning
In dynamic and unstructured environments, mobile robots need to generate safe and efficient trajectories in real time, which poses significant challenges due to the uncertainty of surrounding obstacles. To address this, this article presents a real-time obstacle avoidance trajectory planning method, built upon a spatio-temporal graph network that integrates temporal modeling with graph attention mechanisms. The proposed network captures both temporal dynamics and spatial structural dependencies in dynamic environments by integrating a temporal information module based on long short-term memory (LSTM) and a spatial module based on relational graph attention networks (RGAT). On the whole, the approach follows a two-phase pipeline. In the offline phase, a high-quality trajectory dataset is constructed to represent the heterogeneous state graph of the robot and surrounding obstacles. Then the dataset is used to train the spatio-temporal network, which learns to map environment-state graphs to optimal control commands. In the online phase, the trained network is deployed on the robot to perform real-time perception, decision-making, and control, forming a closed-loop trajectory optimization process. Extensive experiments in both simulated and real-world scenarios demonstrate that the proposed method achieves high-quality trajectory planning, robust obstacle avoidance, and fast generalization under multi-obstacle and sudden disturbance conditions, while maintaining low computational overhead.
- 10 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (18) , 38795-38803
4WIDS-MAPF: Multiagent Pathfinding for Four-Wheel Independent Drive/Steering Robots
Modern autonomous systems face significant challenges in coordinating multiple agents within complex environments, especially under nonholonomic constraints and kinodynamic motion planning demands. In particular, four-wheel independent drive/steering (4WIDS) robots, with their multimodal locomotion and nonholonomic kinematics, introduce new complexity to multiagent pathfinding problems in continuous space. This study addresses the critical challenge of generating collision-free, dynamically feasible paths for multi-4WIDS robot systems. We propose a hierarchical multiagent path finding (MAPF) framework that explicitly tackles two core limitations in existing methods: 1) a lack of physically realistic interagent conflict modeling; and 2) the inability to account for motion mode switching costs in kinodynamic path planning. At the upper level, we introduce a continuous-space binary conflict tree for resolving space–time collisions using physical dimensions and motion feasibility. At the lower level, we implement a hybrid A* search over a motion primitive database that considers mode-switch penalties and kinematic constraints. To improve search performance, we introduce two novel mechanisms: 1) a focused search factor for directional exploration and 2) an adaptive heuristic weighting factor to balance optimality and computational speed. Extensive experiments, including benchmark comparisons, ablation studies, and sensitivity analysis, validate the proposed method’s superior performance in interagent conflict resolution, real-time feasibility, and path quality.
- 10 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (18) , 38795-38803
4WIDS-MAPF: Multiagent Pathfinding for Four-Wheel Independent Drive/Steering Robots
Modern autonomous systems face significant challenges in coordinating multiple agents within complex environments, especially under nonholonomic constraints and kinodynamic motion planning demands. In particular, four-wheel independent drive/steering (4WIDS) robots, with their multimodal locomotion and nonholonomic kinematics, introduce new complexity to multiagent pathfinding problems in continuous space. This study addresses the critical challenge of generating collision-free, dynamically feasible paths for multi-4WIDS robot systems. We propose a hierarchical multiagent path finding (MAPF) framework that explicitly tackles two core limitations in existing methods: 1) a lack of physically realistic interagent conflict modeling; and 2) the inability to account for motion mode switching costs in kinodynamic path planning. At the upper level, we introduce a continuous-space binary conflict tree for resolving space–time collisions using physical dimensions and motion feasibility. At the lower level, we implement a hybrid A* search over a motion primitive database that considers mode-switch penalties and kinematic constraints. To improve search performance, we introduce two novel mechanisms: 1) a focused search factor for directional exploration and 2) an adaptive heuristic weighting factor to balance optimality and computational speed. Extensive experiments, including benchmark comparisons, ablation studies, and sensitivity analysis, validate the proposed method’s superior performance in interagent conflict resolution, real-time feasibility, and path quality.