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


Chengxu Zhou has a total of 104 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Advantage-Weighted Teacher-Student Framework for Agile Quadruped Parkour

    by Hongbo Li, Joshua O’HAra, Maria Stamatopoulou, Chengxu Zhou, Dimitrios Kanoulas

  • Open Access

    Deep reinforcement learning for robotic bipedal locomotion: a brief survey

    by Lingfan Bao, Joseph Humphreys, Tianhu Peng, Chengxu Zhou

    Bipedal robots are gaining global recognition due to their potential applications and the rapid advancements in artificial intelligence, particularly through deep reinforcement learning (DRL). While DRL has significantly advanced bipedal locomotion, the development of a unified framework capable of handling a wide range of tasks remains an ongoing challenge. This survey systematically categorises, compares, and analyses existing DRL frameworks for bipedal locomotion, organising them into end-to-end and hierarchical control schemes. End-to-end frameworks are evaluated based on their learning approaches, whereas hierarchical frameworks are examined in terms of their layered structures that integrate learning-based and traditional model-based methods. We provide a detailed evaluation of the composition, strengths, limitations, and capabilities of each framework. Furthermore, this survey identifies key research gaps and proposes future directions aimed at creating a more integrated and efficient unified framework for bipedal locomotion, with broad applicability in real-world environments.


  • Open Access

    E-SDS: Environment-aware See it, Do it, Sorted - Automated Environment-Aware Reinforcement Learning for Humanoid Locomotion

    by Enis Yalcin, Joshua O'Hara, Maria Stamatopoulou, Chengxu Zhou, Dimitrios Kanoulas

    Vision-language models (VLMs) show promise in automating reward design in humanoid locomotion, which could eliminate the need for tedious manual engineering. However, current VLM-based methods are essentially "blind", as they lack the environmental perception required to navigate complex terrain. We present E-SDS (Environment-aware See it, Do it, Sorted), a framework that closes this perception gap. E-SDS integrates VLMs with real-time terrain sensor analysis to automatically generate reward functions that facilitate training of robust perceptive locomotion policies, grounded by example videos. Evaluated on a Unitree G1 humanoid across four distinct terrains (simple, gaps, obstacles, stairs), E-SDS uniquely enabled successful stair descent, while policies trained with manually-designed rewards or a non-perceptive automated baseline were unable to complete the task. In all terrains, E-SDS also reduced velocity tracking error by 51.9-82.6%. Our framework reduces the human effort of reward design from days to less than two hours while simultaneously producing more robust and capable locomotion policies.

  • Open Access

    Self-Motivated Growing Neural Network for Adaptive Architecture via Local Structural Plasticity

    by Yiyang Jia, Chengxu Zhou

    Control policies in deep reinforcement learning are often implemented with fixed-capacity multilayer perceptrons trained by backpropagation, which lack structural plasticity and depend on global error signals. This paper introduces the Self-Motivated Growing Neural Network (SMGrNN), a controller whose topology evolves online through a local Structural Plasticity Module (SPM). The SPM monitors neuron activations and edge-wise weight update statistics over short temporal windows and uses these signals to trigger neuron insertion and pruning, while synaptic weights are updated by a standard gradient-based optimizer. This allows network capacity to be regulated during learning without manual architectural tuning. SMGrNN is evaluated on control benchmarks via policy distillation. Compared with multilayer perceptron baselines, it achieves similar or higher returns, lower variance, and task-appropriate network sizes. Ablation studies with growth disabled and growth-only variants isolate the role of structural plasticity, showing that adaptive topology improves reward stability. The local and modular design of SPM enables future integration of a Hebbian plasticity module and spike-timing-dependent plasticity, so that SMGrNN can support both artificial and spiking neural implementations driven by local rules.

  • Open Access

    Sim-to-Real Transfer in Deep Reinforcement Learning for Bipedal Locomotion

    by Lingfan Bao, Tianhu Peng, Chengxu Zhou

    This chapter addresses the critical challenge of simulation-to-reality (sim-to-real) transfer for deep reinforcement learning (DRL) in bipedal locomotion. After contextualizing the problem within various control architectures, we dissect the ``curse of simulation'' by analyzing the primary sources of sim-to-real gap: robot dynamics, contact modeling, state estimation, and numerical solvers. Building on this diagnosis, we structure the solutions around two complementary philosophies. The first is to shrink the gap through model-centric strategies that systematically improve the simulator's physical fidelity. The second is to harden the policy, a complementary approach that uses in-simulation robustness training and post-deployment adaptation to make the policy inherently resilient to model inaccuracies. The chapter concludes by synthesizing these philosophies into a strategic framework, providing a clear roadmap for developing and evaluating robust sim-to-real solutions.

  • More Precise and Faster: Dual-Scale Teleoperation for Manipulator in Large Workspace

    by Pengyu Sun, Weihua Li, Jun Li, Yiqun Liu, Jianfeng Wang, Liang Ding, Chengxu Zhou

    In practical robotic applications, most tasks require a combination of large-range motion and fine operation. Effectively coordinating these two aspects poses a significant challenge due to the mismatch between the limited workspace of the leader robot and the expansive workspace of the follower manipulator. To address this issue, we propose a dual-scale teleoperation framework that enables the seamless integration of large-range movement and fine operation. Furthermore, we design an adaptive force feedback strategy based on fuzzy logic, which dynamically allocates environmental contact and constraint forces between the dual leaders with different mapping scales, ensuring closed-loop control of the system. A comprehensive analysis of the framework's stability and transparency is provided. Finally, the proposed force feedback teleoperation framework is experimentally validated against existing methods. In the fixed-point alignment task, the proposed method achieves a success rate of 85.7% and reduces completion time by approximately 10%. In the narrow passage navigation task, the manipulator successfully passes through a 120 mm-wide channel (with a manipulator width of 115 mm), while significantly reducing the number of collisions. These experimental results demonstrate the effectiveness of the proposed approach in achieving fine operations within large workspaces.


  • Open Access

    Special Issue “Legged Robots into the Real World, 2nd Edition”

    by Chengxu Zhou

    Legged robots are widely recognised as one of the most ambitious frontiers in robotics, promising mobility and adaptability in environments where wheels and tracks cannot operate

  • Open Access

    Learning to adapt through bio-inspired gait strategies for versatile quadruped locomotion

    by Joseph Humphreys, Chengxu Zhou

    Legged robots must adapt their gait to navigate unpredictable environments, a challenge that animals master with ease. However, most deep reinforcement learning (DRL) approaches to quadruped locomotion rely on a fixed gait, limiting adaptability to changes in terrain and dynamic state. Here we show that integrating three core principles of animal locomotion-gait transition strategies, gait memory and real-time motion adjustments enables a DRL control framework to fluidly switch among multiple gaits and recover from instability, all without external sensing. Our framework is guided by biomechanics-inspired metrics that capture efficiency, stability and system limits, which are unified to inform optimal gait selection. The resulting framework achieves blind zero-shot deployment across diverse, real-world terrains and substantially outperforms baseline controllers. By embedding biological principles into data-driven control, this work marks a step towards robust, efficient and versatile robotic locomotion, highlighting how animal motor intelligence can shape the next generation of adaptive machines.