Tianbo Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Tianbo Li has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Siqing Sun
School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an 710072, China
5 shared publications - Huachao Dong
School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an 710072, China
3 shared publications - Dezhou Qin
School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an 710072, China
2 shared publications - Aiqin Wang
State Key Laboratory of Catalysis, Dalian Institute of Chemical Physics, Chinese Academy of Sciences, No. 457 Zhongshan Road, Dalian 116023, China
1 shared publication - Bing Han
Shandong University - Institute of Basic Medical Sciences
1 shared publication - Botao Qiao
Dalian National Laboratory For Clean Energy Dalian Institute of Chemical Physics Chinese Academy of Sciences Dalian Liaoning P. R. China
1 shared publication
Latest Publications
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/CAA Journal of Automatica Sinica
- Vol. 13 (10) , 2414-2416
Knowledge-Assistant Deep Reinforcement Learning for Multi-Agent Region Protection
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/CAA Journal of Automatica Sinica
- Vol. 13 (10) , 2414-2416
Knowledge-Assistant Deep Reinforcement Learning for Multi-Agent Region Protection
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 139914-139929
Velocity Prediction in Hypersonic Flow via Prior-Guided Data Fusion and Physics-Informed Learning
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 139914-139929
Open AccessVelocity Prediction in Hypersonic Flow via Prior-Guided Data Fusion and Physics-Informed Learning
- Open Access
- 19 November 2024
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 12 (11) , 2094
Model-Driven Cooperative Path Planning for Dynamic Target Searching of Unmanned Unterwater Vehicle Formation
With the increasing complexity of ocean missions, using multiple unmanned underwater vehicles to collaborate in executing tasks has become an effective way to improve the overall efficiency of ocean operations. Current research on path planning for multiple unmanned underwater vehicles mainly focuses on the basis of particle models or fully known environmental information, while research directions mainly focus on single indicators such as completion time and energy consumption. This paper first constructs a UUV model and a task scenario with detection success rate as the objective function. Then, a parameterization method based on a spiral search path was proposed for designing variables. A hierarchical control strategy is designed to ensure handle formation constraints. A general optimization framework for task scenarios has been constructed and combined with algorithms to solve optimization problems. Finally, this study compared and analyzed the performance of different optimization algorithms under the optimization framework, evaluated the optimization results of different search strategies, and explored the impact of dynamic objectives on the detection success rate. The results showed that the optimized path had a search success rate that increased by more than 50% compared to the direct path and the cover search path, which verified the effectiveness of the proposed method and strategy.
- 19 November 2024
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 12 (11) , 2094
Open AccessModel-Driven Cooperative Path Planning for Dynamic Target Searching of Unmanned Unterwater Vehicle Formation
With the increasing complexity of ocean missions, using multiple unmanned underwater vehicles to collaborate in executing tasks has become an effective way to improve the overall efficiency of ocean operations. Current research on path planning for multiple unmanned underwater vehicles mainly focuses on the basis of particle models or fully known environmental information, while research directions mainly focus on single indicators such as completion time and energy consumption. This paper first constructs a UUV model and a task scenario with detection success rate as the objective function. Then, a parameterization method based on a spiral search path was proposed for designing variables. A hierarchical control strategy is designed to ensure handle formation constraints. A general optimization framework for task scenarios has been constructed and combined with algorithms to solve optimization problems. Finally, this study compared and analyzed the performance of different optimization algorithms under the optimization framework, evaluated the optimization results of different search strategies, and explored the impact of dynamic objectives on the detection success rate. The results showed that the optimized path had a search success rate that increased by more than 50% compared to the direct path and the cover search path, which verified the effectiveness of the proposed method and strategy.
- Open Access
- 23 October 2024
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 12 (11) , 1896
A Balanced Mission Planning for Multiple Unmanned Underwater Vehicles in Complex Marine Environments
The collaboration of a multiple unmanned underwater vehicles (multi-UUVs) system has attracted widespread attention in recent years, as it can overcome the limitations of a single UUV and enhance mission completion efficiency. Oriented towards patrol and exploration missions with multiple waypoints, this paper proposes a balanced mission planning strategy, aiming to improve mission quality while reducing mission time for multi-UUVs. Firstly, due to the uneven performance of the two optimization objectives, a quick initialization screening method is employed specifically for mission quality to reduce the mission space. Secondly, to ensure mission load distribution and collaboration among multi-UUVs, and ease the difficulty in solving the issues of mission allocation and route planning, a balanced bi-level mission planning method based on regional segmentation is proposed. Finally, applicable weight evaluation criteria are utilized to evaluate the feasible solution set and determine the optimal solution. The efficacy of the balanced mission planning strategy is substantiated through comprehensive numerical simulations in a complex 2D marine environment.
- 23 October 2024
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 12 (11) , 1896
Open AccessA Balanced Mission Planning for Multiple Unmanned Underwater Vehicles in Complex Marine Environments
The collaboration of a multiple unmanned underwater vehicles (multi-UUVs) system has attracted widespread attention in recent years, as it can overcome the limitations of a single UUV and enhance mission completion efficiency. Oriented towards patrol and exploration missions with multiple waypoints, this paper proposes a balanced mission planning strategy, aiming to improve mission quality while reducing mission time for multi-UUVs. Firstly, due to the uneven performance of the two optimization objectives, a quick initialization screening method is employed specifically for mission quality to reduce the mission space. Secondly, to ensure mission load distribution and collaboration among multi-UUVs, and ease the difficulty in solving the issues of mission allocation and route planning, a balanced bi-level mission planning method based on regional segmentation is proposed. Finally, applicable weight evaluation criteria are utilized to evaluate the feasible solution set and determine the optimal solution. The efficacy of the balanced mission planning strategy is substantiated through comprehensive numerical simulations in a complex 2D marine environment.
- Open Access
- 22 February 2024
- Published by Springer Nature in Complex & Intelligent Systems
- Vol. 10 (3) , 3727-3742
A modified evolutionary reinforcement learning for multi-agent region protection with fewer defenders
Autonomous region protection is a significant research area in multi-agent systems, aiming to empower defenders in preventing intruders from accessing specific regions. This paper presents a Multi-agent Region Protection Environment (MRPE) featuring fewer defenders, defender damages, and intruder evasion strategies targeting defenders. MRPE poses challenges for traditional protection methods due to its high nonstationarity and limited interception time window. To surmount these hurdles, we modify evolutionary reinforcement learning, giving rise to the corresponding multi-agent region protection method (MRPM). MRPM amalgamates the merits of evolutionary algorithms and deep reinforcement learning, specifically leveraging Differential Evolution (DE) and Multi-Agent Deep Deterministic Policy Gradient (MADDPG). DE facilitates diverse sample exploration and overcomes sparse rewards, while MADDPG trains defenders and expedites the DE convergence process. Additionally, an elite selection strategy tailored for multi-agent systems is devised to enhance defender collaboration. The paper also presents ingenious designs for the fitness and reward functions to effectively drive policy optimizations. Finally, extensive numerical simulations are conducted to validate the effectiveness of MRPM.
- 22 February 2024
- Published by Springer Nature in Complex & Intelligent Systems
- Vol. 10 (3) , 3727-3742
Open AccessA modified evolutionary reinforcement learning for multi-agent region protection with fewer defenders
Autonomous region protection is a significant research area in multi-agent systems, aiming to empower defenders in preventing intruders from accessing specific regions. This paper presents a Multi-agent Region Protection Environment (MRPE) featuring fewer defenders, defender damages, and intruder evasion strategies targeting defenders. MRPE poses challenges for traditional protection methods due to its high nonstationarity and limited interception time window. To surmount these hurdles, we modify evolutionary reinforcement learning, giving rise to the corresponding multi-agent region protection method (MRPM). MRPM amalgamates the merits of evolutionary algorithms and deep reinforcement learning, specifically leveraging Differential Evolution (DE) and Multi-Agent Deep Deterministic Policy Gradient (MADDPG). DE facilitates diverse sample exploration and overcomes sparse rewards, while MADDPG trains defenders and expedites the DE convergence process. Additionally, an elite selection strategy tailored for multi-agent systems is devised to enhance defender collaboration. The paper also presents ingenious designs for the fitness and reward functions to effectively drive policy optimizations. Finally, extensive numerical simulations are conducted to validate the effectiveness of MRPM.
- Open Access
- 18 November 2019
- Published by Springer Nature in Science China Materials
- Vol. 63 (6) , 959-964
Pd1/CeO2 single-atom catalyst for alkoxycarbonylation of aryl iodides
- 18 November 2019
- Published by Springer Nature in Science China Materials
- Vol. 63 (6) , 959-964
Open AccessPd1/CeO2 single-atom catalyst for alkoxycarbonylation of aryl iodides
- Open Access
- 10 October 2018
- Published by IntechOpen
Voltage-Gated Sodium Channels in Drug Discovery
Voltage-gated sodium channels (Nav) control the initiation and propagation of action potential, and thus mediate a broad spectrum of physiological processes, including central and peripheral nervous systems’ function, skeletal muscle contraction, and heart rhythm. Recent advances in elucidating the molecular basis of channelopathies implicating Nav channels are the most appealing druggable targets for pain and many other pathology conditions. This chapter overviews Nav super family from genetic evolution, distribution, human diseases/pathology association, highlighting the most recent structure function breakthrough. The second section will discuss current small and large Nav modulators, including traditional nonselective pore blockers, intracellular modulators, and extracellular modulators.
- 10 October 2018
- Published by IntechOpen
Open AccessVoltage-Gated Sodium Channels in Drug Discovery
Voltage-gated sodium channels (Nav) control the initiation and propagation of action potential, and thus mediate a broad spectrum of physiological processes, including central and peripheral nervous systems’ function, skeletal muscle contraction, and heart rhythm. Recent advances in elucidating the molecular basis of channelopathies implicating Nav channels are the most appealing druggable targets for pain and many other pathology conditions. This chapter overviews Nav super family from genetic evolution, distribution, human diseases/pathology association, highlighting the most recent structure function breakthrough. The second section will discuss current small and large Nav modulators, including traditional nonselective pore blockers, intracellular modulators, and extracellular modulators.