ZLZhibin Li

Zhibin Li

*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


Zhibin Li has a total of 117 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • eGAIT: Multi-Skilled Policy for Energy-Efficient Gait Transitions

    by Maria Stamatopoulou, Daniel Tan, Rokas Bendikas, Valerio Modugno, Zhibin Li, Dimitrios Kanoulas

    Achieving adaptive, multi-skilled, and energy-efficient locomotion is vital for advancing the operation of autonomous quadrupedal systems. This study presents eGAIT, a unified multi-skilled policy enabling energy-efficient and stable gait transitions across nine non-monotonic, velocity-optimized gaits, in response to dynamic velocity commands. The framework leverages a hybrid control architecture that integrates model-based and learning-based methods to address the entire locomotion pipeline. An MPC-based gait generator produces velocity-optimized trajectories, which are imitated through Proximal Policy Optimization (PPO), driven by a Adversarial Motion Prior (AMP) style reward to train distinct policies for specific velocity ranges. These policies are unified through a Hierarchical Reinforcement Learning (HRL) framework featuring a novel modified Deep Q-Network (eDQN) for real-time velocity-to-policy mapping. Training efficiency is enhanced by an auxiliary selector layer that guides velocity-policy mapping, while a sparsely activated stability reward mechanism ensures smooth gait transitions by incorporating geometric and rotational stability. Extensively validated in simulation and on a Unitree Go1 robot, eGAIT achieves a 100% success rate in velocity-to-policy mapping, a 35% improvement in energy efficiency, a 31% improvement in both velocity tracking and stability compared to the next best state-of-the-art method. This work advances autonomous quadrupedal locomotion, enabling longer, more efficient, and stable operations in dynamic environments. Supplementary materials and visualizations related to the paper can be found at: https://github.com/RPL-CS-UCL/egait/.

  • Open Access

    3D Feature Distillation with Object-Centric Priors

    by Georgios Tziafas, Yucheng Xu, Zhibin Li, Hamidreza Kasaei

    Grounding natural language to the physical world is a ubiquitous topic with a widerange of applications in computer vision and robotics. Recently, 2D vision-languagemodels such as CLIP have been widely popularized, due to their impressivecapabilities for open-vocabulary grounding in 2D images. Subsequent works aimto elevate 2D CLIP features to 3D via feature distillation, but either learn neuralfields that are scene-specific and hence lack generalization, or focus on indoor roomscan data that require access to multiple camera views, which is not practical inrobot manipulation scenarios. Additionally, related methods typically fuse featuresat pixel-level and assume that all camera views are equally informative. In thiswork, we show that this approach leads to sub-optimal 3D features, both in termsof grounding accuracy, as well as segmentation crispness. To alleviate this, wepropose a multi-view feature fusion strategy that employs object-centric priors toeliminate uninformative views based on semantic information, and fuse featuresat object-level via instance segmentation masks. To distill our object-centric3D features, we generate a large-scale synthetic multi-view dataset of clutteredtabletop scenes, spawning 15k scenes from over 3300 unique object instances,which we make publicly available. We show that our method reconstructs 3DCLIP features with improved grounding capacity and spatial consistency, whiledoing so from single-view RGB-D, thus departing from the assumption of multiplecamera views at test time. Finally, we show that our approach can generalize tonovel tabletop domains and be re-purposed for 3D instance segmentation withoutfine-tuning, and demonstrate its utility for language-guided robotic grasping in clutter. Released assets and supplementary material is made available at thewebsite https://gtziafas.github.io/DROP_project/.

  • RoboBallet: Planning for multirobot reaching with graph neural networks and reinforcement learning

    by Matthew Lai, Keegan Go, Zhibin Li, Torsten Kröger, Stefan Schaal, Kelsey Allen, Jonathan Scholz

    Modern robotic manufacturing requires collision-free coordination of multiple robots to complete numerous tasks in shared, obstacle-rich workspaces. Although individual tasks may be simple in isolation, automated joint task allocation, scheduling, and motion planning under spatiotemporal constraints remain computationally intractable for classical methods at real-world scales. Existing multiarm systems deployed in industry rely on human intuition and experience to design feasible trajectories manually in a labor-intensive process. To address this challenge, we propose a reinforcement learning (RL) framework to achieve automated task and motion planning, tested in an obstacle-rich environment with eight robots performing 40 reaching tasks in a shared workspace, where any robot can perform any task in any order. Our approach builds on a graph neural network (GNN) policy trained via RL on procedurally generated environments with diverse obstacle layouts, robot configurations, and task distributions. It uses a graph representation of scenes and a graph policy neural network trained through RL to generate trajectories of multiple robots, jointly solving the subproblems of task allocation, scheduling, and motion planning. Trained on large randomly generated task sets in simulation, our policy generalizes zero-shot to unseen settings with varying robot placements, obstacle geometries, and task poses. We further demonstrate that the high-speed capability of our solution enables its use in workcell layout optimization, improving solution times. The speed and scalability of our planner also open the door to capabilities such as fault-tolerant planning and online perception-based replanning, where rapid adaptation to dynamic task sets is required.


  • AI search, physician removal: Bronchoscopy robot bridges collaboration in foreign body aspiration

    by Lilu Liu, Jingyu Zhang, Fei Wang, Jiyu Yu, Yuxiang Cui, Zhibin Li, Jian Hu, Rong Xiong, Haojian Lu, Yue Wang

    Bronchial foreign body aspiration is a life-threatening condition with a high incidence across diverse populations, requiring urgent diagnosis and treatment. However, the limited availability of skilled practitioners and advanced medical equipment in community clinics and underdeveloped regions underscores the broader challenges in emergency care. Here, we present a cost-effective robotic bronchoscope capable of computed tomography (CT)–free, artificial intelligence (AI)–driven foreign body search and doctor-collaborated removal over long distances via fifth-generation (5G) communication. The system is built around a low-cost (<5000 USD), portable (<2 kilograms) bronchoscope robotic platform equipped with a 3.3-millimeter-diameter catheter and 1-millimeter biopsy forceps designed for safe pulmonary search and foreign body removal. Our AI algorithm, which integrates classical data structures with modern machine learning techniques, enables thorough CT-free lung coverage. The tree structure is leveraged to memorize a compact exploration process and guide the decision-making. Both virtual and physical simulations demonstrate the system’s effective autonomous foreign body search, minimizing bronchial wall contact to reduce patient discomfort. In a remote procedure, a physician in Hangzhou successfully retrieved a foreign body from a live pig located 1500 kilometers away in Chengdu using 5G communication, highlighting effective collaboration of AI, robotics, and human experts. We anticipate that this 5G-enabled, low-cost, AI expert–collaborated robotic platform has notable potential to reduce medical disparities, enhance emergency care, improve patient outcomes, decrease physician workload, and streamline medical procedures through the automation of routine tasks.


  • Achieving Dexterous Bidirectional Interaction in Uncertain Conditions for Medical Robotics

    by Carlo Tiseo, Quentin Rouxel, Martin Asenov, Keyhan Kouhkiloui Babarahmati, Subramanian Ramamoorthy, Zhibin Li, Michael Mistry

    Medical robotics can help improve the reach of healthcare services. A challenge for medical robots is their complex physical interaction. This work evaluates a recently introduced control architecture based on Fractal Impedance Control (FIC) in medical applications. The deployed FIC architecture is robust to delay between the master and the replica robots and can switch online between an admittance and impedance behaviour. Our experiments analyse three scenarios: teleoperated surgery, rehabilitation, and remote ultrasound scan. The experiments did not require any adjustment of the robot tuning, which is essential in medical applications where the operators do not have an engineering background. Our results show that it is possible to teleoperate the robot to perform remote occupational therapy, operate a scalpel, and use an ultrasound scan. However, our experiments also highlighted the need for a better robot embodiment to control the system precisely in 3D dynamic tasks.


  • Open Access

    DexSkills: Skill Segmentation Using Haptic Data for Learning Autonomous Long-Horizon Robotic Manipulation Tasks

    by Xiaofeng Mao, Gabriele Giudici, Claudio Coppola, Kaspar Althoefer, Ildar Farkhatdinov, Zhibin Li, Lorenzo Jamone

    Effective execution of long-horizon tasks with dexterous robotic hands remains a significant challenge in real-world problems. While learning from human demonstrations have shown encouraging results, they require extensive data collection for training. Hence, decomposing long-horizon tasks into reusable primitive skills is a more efficient approach. To achieve so, we developed DexSkills, a novel supervised learning framework that addresses long-horizon dexterous manipulation tasks using primitive skills. DexSkills is trained to recognize and replicate a select set of skills using human demonstration data, which can then segment a demonstrated long-horizon dexterous manipulation task into a sequence of primitive skills to achieve one-shot execution by the robot directly. Significantly, DexSkills operates solely on proprioceptive and tactile data, i.e., haptic data. Our real-world robotic experiments show that DexSkills can accurately segment skills, thereby enabling autonomous robot execution of a diverse range of tasks.

  • Open Access

    Intrinsic Language-Guided Exploration for Complex Long-Horizon Robotic Manipulation Tasks

    by Eleftherios Triantafyllidis, Filippos Christianos, Zhibin Li

    Current reinforcement learning algorithms struggle in sparse and complex environments, most notably in long-horizon manipulation tasks entailing a plethora of different sequences. In this work, we propose the Intrinsically Guided Exploration from Large Language Models (IGE-LLMs) framework. By leveraging LLMs as an assistive intrinsic reward, IGE-LLMs guides the exploratory process in reinforcement learning to address intricate long-horizon with sparse rewards robotic manipulation tasks. We evaluate our framework and related intrinsic learning methods in an environment challenged with exploration, and a complex robotic manipulation task challenged by both exploration and long-horizons. Results show IGE-LLMs (i) exhibit notably higher performance over related intrinsic methods and the direct use of LLMs in decision-making, (ii) can be combined and complement existing learning methods highlighting its modularity, (iii) are fairly insensitive to different intrinsic scaling parameters, and (iv) maintain robustness against increased levels of uncertainty and horizons.

  • Open Access

    Value Functions are Control Barrier Functions: Verification of Safe Policies using Control Theory

    by Daniel C. H. Tan, Fernando Acero, Robert McCarthy, Dimitrios Kanoulas, Zhibin Li

    Guaranteeing safe behaviour of reinforcement learning (RL) policies poses significant challenges for safety-critical applications, despite RL's generality and scalability. To address this, we propose a new approach to apply verification methods from control theory to learned value functions. By analyzing task structures for safety preservation, we formalize original theorems that establish links between value functions and control barrier functions. Further, we propose novel metrics for verifying value functions in safe control tasks and practical implementation details to improve learning. Our work presents a novel method for certificate learning, which unlocks a diversity of verification techniques from control theory for RL policies, and marks a significant step towards a formal framework for the general, scalable, and verifiable design of RL-based control systems. Code and videos are available at this https url: https://rl-cbf.github.io/

  • Design of Adaptive Control Law for Ship Second-Order Nonlinear Systems Based on Backstepping Method

    by Shengjie Wang, Zhibin Li, Wencheng Song, Bohan Xu

    For nonlinear systems, backstepping control algorithm is a widely used control algorithm whose basic principle achieves control by recursion. By dividing the complex system into several independent sub-systems, controlling the sub-systems individually and using the Lyapunov function to judge the stability of the system, the control of the whole nonlinear system is achieved. In this paper, the second-order nonlinear system of ship heading is studied. Combining backstepping with adaptive thought while considering system interference items. The unknown parameters of the system are traced and estimated, and the designed controller is simulated by Simulink. The simulation results validate that the designed controller has better stability and control performance, while reducing the impact of system disturbance.

  • Open Access

    Language-guided Robot Grasping: CLIP-based Referring Grasp Synthesis in Clutter

    by Georgios Tziafas, Yucheng Xu, Arushi Goel, Mohammadreza Kasaei, Zhibin Li, Hamidreza Kasaei

    Robots operating in human-centric environments require the integration of visual grounding and grasping capabilities to effectively manipulate objects based on user instructions. This work focuses on the task of referring grasp synthesis, which predicts a grasp pose for an object referred through natural language in cluttered scenes. Existing approaches often employ multi-stage pipelines that first segment the referred object and then propose a suitable grasp, and are evaluated in private datasets or simulators that do not capture the complexity of natural indoor scenes. To address these limitations, we develop a challenging benchmark based on cluttered indoor scenes from OCID dataset, for which we generate referring expressions and connect them with 4-DoF grasp poses. Further, we propose a novel end-to-end model (CROG) that leverages the visual grounding capabilities of CLIP to learn grasp synthesis directly from image-text pairs. Our results show that vanilla integration of CLIP with pretrained models transfers poorly in our challenging benchmark, while CROG achieves significant improvements both in terms of grounding and grasping. Extensive robot experiments in both simulation and hardware demonstrate the effectiveness of our approach in challenging interactive object grasping scenarios that include clutter.