Selected Publications

1. 

   Lateral flexion of a compliant spine improves motor performance in a bioinspired mouse robot

   Zhenshan Bing^*, Alex Rohregger, Florian Walter, Yuhong Huang, Peer Lucas, Fabrice O. Morin, Kai Huang^*, and Alois Knoll^*

   Science Robotics 2023

   Abs Bib

   A flexible spine is critical to the motion capability of most animals and plays a pivotal role in their agility. Although state-of-the-art legged robots have already achieved very dynamic and agile movement solely relying on their legs, they still exhibit the type of stiff movement that compromises movement efficiency. The integration of a flexible spine thus appears to be a promising approach to improve their agility, especially for small and underactuated quadruped robots that are underpowered because of size limitations. Here, we show that the lateral flexion of a compliant spine can promote both walking speed and maneuver agility for a neurorobotic mouse (NeRmo). We present NeRmo as a biomimetic robotic mouse that mimics the morphology of biological mice and their muscle-tendon actuation system. First, by leveraging the lateral flexion of the compliant spine, NeRmo can greatly increase its static stability in an initially unstable configuration by adjusting its posture. Second, the lateral flexion of the spine can also effectively extend the stride length of a gait and therefore improve the walking speeds of NeRmo. Finally, NeRmo shows agile maneuvers that require both a small turning radius and fast walking speed with the help of the spine. These results advance our understanding of spine-based quadruped locomotion skills and highlight promising design concepts to develop more agile legged robots. Lateral flexion of a compliant spine can improve motor skills of a bioinspired mouse robot.

   @article{doi:10.1126/scirobotics.adg7165,
     author = {<b>Bing</b><sup>*</sup>, <b>Zhenshan</b> and Rohregger, Alex and Walter, Florian and Huang, Yuhong and Lucas, Peer and Morin, Fabrice O. and Huang<sup>*</sup>, Kai and Knoll<sup>*</sup>, Alois},
     title = {Lateral flexion of a compliant spine improves motor performance in a bioinspired mouse robot},
     journal = {<b>Science Robotics</b>},
     year = {2023},
     volume = {8},
     month = {},
     number = {85},
     pages = {eadg7165},
     issn = {},
     doi = {10.1126/scirobotics.adg7165},
     language = {},
     keywords = {},
   }

2. 

   Preserving and combining knowledge in robotic lifelong reinforcement learning

   Yuan Meng, Zhenshan Bing^*, Xiangtong Yao, Kejia Chen, Kai Huang, Yang Gao, Fuchun Sun, and Alois Knoll

   Nature Machine Intelligence 2025

   Abs Bib HTML PDF Code

   Humans can continually accumulate knowledge and develop increasingly complex behaviours and skills throughout their lives, which is a capability known as ‘lifelong learning’. Although this lifelong learning capability is considered an essential mechanism that makes up general intelligence, recent advancements in artificial intelligence predominantly excel in narrow, specialized domains and generally lack this lifelong learning capability. Here we introduce a robotic lifelong reinforcement learning framework that addresses this gap by developing a knowledge space inspired by the Bayesian non-parametric domain. In addition, we enhance the agent’s semantic understanding of tasks by integrating language embeddings into the framework. Our proposed embodied agent can consistently accumulate knowledge from a continuous stream of one-time feeding tasks. Furthermore, our agent can tackle challenging real-world long-horizon tasks by combining and reapplying its acquired knowledge from the original tasks stream. The proposed framework advances our understanding of the robotic lifelong learning process and may inspire the development of more broadly applicable intelligence.

   @article{Meng2025,
     author = {Meng, Yuan and <b>Bing</b><sup>*</sup>, <b>Zhenshan</b> and Yao, Xiangtong and Chen, Kejia and Huang, Kai and Gao, Yang and Sun, Fuchun and Knoll, Alois},
     year = {2025},
     date = {2025-02-05},
     title = {Preserving and combining knowledge in robotic lifelong reinforcement learning},
     journal = {<b>Nature Machine Intelligence</b>},
     issn = {2522-5839},
     url = {https://doi.org/10.1038/s42256-025-00983-2},
     doi = {10.1038/s42256-025-00983-2},
   }

3. 

   Context-Based Meta-Reinforcement Learning With Bayesian Nonparametric Models

   Zhenshan Bing, Yuqi Yun, Kai Huang, and Alois Knoll

   IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2024

   Bib

   @article{10495171,
     author = {<b>Bing</b>, <b>Zhenshan</b> and Yun, Yuqi and Huang, Kai and Knoll, Alois},
     journal = {<b>IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)</b>},
     title = {Context-Based Meta-Reinforcement Learning With Bayesian Nonparametric Models},
     year = {2024},
     volume = {46},
     number = {10},
     pages = {6948-6965},
     keywords = {Task analysis;Clustering algorithms;Training;Optimization;Adaptation models;Markov decision processes;Inference algorithms;Meta-reinforcement learning;task inference;task adaptation;Bayesian nonparametric model;robotic control},
     doi = {10.1109/TPAMI.2024.3386780},
   }

4. 

   Simulation to Real: Learning Energy-Efficient Slithering Gaits for a Snake-Like Robot

   Zhenshan Bing, Long Cheng, Kai Huang, and Alois Knoll

   IEEE Robotics & Automation Magazine 2022

   Bib PDF

   @article{9895427,
     author = {<b>Bing</b>, <b>Zhenshan</b> and Cheng, Long and Huang, Kai and Knoll, Alois},
     journal = {IEEE Robotics & Automation Magazine},
     title = {Simulation to Real: Learning Energy-Efficient Slithering Gaits for a Snake-Like Robot},
     year = {2022},
     volume = {29},
     number = {4},
     pages = {92-103},
     doi = {10.1109/MRA.2022.3204237},
   }

5. 

   Meta-reinforcement learning in non-stationary and dynamic environments

   Zhenshan Bing, David Lerch, Kai Huang, and Alois Knoll

   IEEE Transactions on Pattern Analysis and Machine Intelligence 2022

   Bib HTML PDF Code Video

   @article{bing2022meta,
     title = {Meta-reinforcement learning in non-stationary and dynamic environments},
     author = {<b>Bing</b>, <b>Zhenshan</b> and Lerch, David and Huang, Kai and Knoll, Alois},
     journal = {<b>IEEE Transactions on Pattern Analysis and Machine Intelligence</b>},
     year = {2022},
     publisher = {IEEE},
     video = {},
   }

6. 

   Solving Robotic Manipulation with Sparse Reward Reinforcement Learning via Graph-Based Diversity and Proximity

   Zhenshan Bing, Hongkuan Zhou, Rui Li, Xiaojie Su, Fabrice Oliver Morin, Kai Huang, and Alois Knoll

   IEEE Transactions on Industrial Electronics 2022
7. 

   Toward Cognitive Navigation: Design and Implementation of a Biologically Inspired Head Direction Cell Network

   Zhenshan Bing, Amir EI Sewisy, Genghang Zhuang, Florian Walter, Fabrice O. Morin, Kai Huang, and Alois Knoll

   IEEE Transactions on Neural Networks and Learning Systems 2022
8. 

   Robotic Manipulation in Dynamic Scenarios via Bounding-Box-Based Hindsight Goal Generation

   Zhenshan Bing, Erick Álvarez, Long Cheng, Fabrice O. Morin, Rui Li, Xiaojie Su, Kai Huang, and Alois Knoll

   IEEE Transactions on Neural Networks and Learning Systems 2021
9. 

   Complex Robotic Manipulation via Graph-Based Hindsight Goal Generation

   Zhenshan Bing, Matthias Brucker, Fabrice O. Morin, Rui Li, Xiaojie Su, Kai Huang, and Alois Knoll

   IEEE Transactions on Neural Networks and Learning Systems 2021
10. Neural Networks

    Indirect and direct training of spiking neural networks for end-to-end control of a lane-keeping vehicle

    Zhenshan Bing, Claus Meschede, Guang Chen, Alois Knoll, and Kai Huang

    Neural Networks 2020

    Abs Code

    Building spiking neural networks (SNNs) based on biological synaptic plasticities holds a promising potential for accomplishing fast and energy-efficient computing, which is beneficial to mobile robotic applications. However, the implementations of SNNs in robotic fields are limited due to the lack of practical training methods. In this paper, we therefore introduce both indirect and direct end-to-end training methods of SNNs for a lane-keeping vehicle. First, we adopt a policy learned using the Deep Q-Learning (DQN) algorithm and then subsequently transfer it to an SNN using supervised learning. Second, we adopt the reward-modulated spike-timing-dependent plasticity (R-STDP) for training SNNs directly, since it combines the advantages of both reinforcement learning and the well-known spike-timing-dependent plasticity (STDP). We examine the proposed approaches in three scenarios in which a robot is controlled to keep within lane markings by using an event-based neuromorphic vision sensor. We further demonstrate the advantages of the R-STDP approach in terms of the lateral localization accuracy and training time steps by comparing them with other three algorithms presented in this paper.

11. Nano Energy

    A multi-dimensional tactile perception system based on triboelectric sensors: towards intelligent sorting without seeing

    Tianxiao Xiao, Zhenshan Bing^#, Yansong Wu, Wei Chen, Ziming Zhou, Fan Fang, Suzhe Liang, Renjun Guo, Suo Tu, Guangjiu Pan, and  others

    Nano Energy 2024
12. 

    Modeling Grid Cell Distortions with a Grid Cell Calibration Mechanism

    Daniel Strauß, Zhenshan Bing^#, Genghang Zhuang, Kai Huang, and Alois Knoll

    Cyborg and Bionic Systems 2024
13. 

    Modulating emotional states of rats through a rat-like robot with learned interaction patterns

    Guanglu Jia, Zhe Chen, Yulai Zhang, Zhenshan Bing, Zhenzhen Quan, Xuechao Chen, Alois Knoll, Qiang Huang, and Qing Shi

    Nature Machine Intelligence 2024

    Abs

    Robots, integrated into biological systems as sociable partners, offer promising advancement in the mechanistic understanding of social behaviours. These biohybrid systems bring controllability to help elucidate the underlying biological intelligence previously inaccessible through traditional techniques. However, state-of-the-art interactive robots still struggle to convey multilevel, heterogeneous information within biological systems, making it challenging to mediate the complex interaction process effectively. Here we propose an autonomous, interactive rat-like robot that can engage with freely behaving rats by learning from the anatomical structure, dynamic motions and social interaction of rats. Imitation learning based on animal demonstration enables the robot with subtle templates of social behaviour, allowing it to capture the attention of rats and significantly arouse their interest. It also integrates visual perception, target tracking and behavioural decisions to substantially augment the interaction efficiency. We demonstrate that the robot can interact with rats for a continuous half-hour. Moreover, the robot can modulate the emotional states of rats through different interaction patterns during robot–rat social interaction. These results attest that the proposed interactive robot, with its long-term and repetitive interaction capabilities, overcomes the limitations of natural social interaction within biological systems. Such biohybrid systems capable of modulating the internal states of organisms may open the door to comprehending the ‘social’ interactions between humans and artificial intelligence.