The complexity of a legged robot's environment or task can inform how specialised its gait must be to ensure success. Evolving specialised robotic gaits demands many evaluations - acceptable for computer simulations, but not for physical robots. For some tasks, a more general gait, with lower optimization costs, could be satisfactory. In this paper, we introduce a new type of gait controller where complexity can be set by a single parameter, using a dynamic genotype-phenotype mapping. Low controller complexity leads to conservative gaits, while higher complexity allows more sophistication and high performance for demanding tasks, at the cost of optimization effort. We investigate the new controller on a virtual robot in simulations and do preliminary testing on a real-world robot. We show that having variable complexity allows us to adapt to different optimization budgets. With a high evaluation budget in simulation, a complex controller performs best. Moreover, real-world evolution with a limited evaluation budget indicates that a lower gait complexity is preferable for a relatively simple environment.
Autonomous UAV-Quadruped Docking in Complex Terrains via Active Posture Alignment and Constraint-Aware Control
College of Electronics and Information Engineering, Tongji University（同济大学电子与信息工程学院）；Frontiers Science Center for Intelligent Autonomous Systems, Shanghai（上海智能自主系统前沿科学中心）；School of Logistics Engineering, Shanghai Maritime University（上海 Maritime University物流工程学院）；State Key Laboratory of Autonomous Intelligent Unmanned Systems, Shanghai（上海自主智能无人系统国家重点实验室）
Two-layer adaptive trajectory tracking controller for quadruped robots on slippery terrains
Institute of Computer Science, Foundation for Research and Technology–Hellas（希腊基础研究与技术基金会计算机科学研究所）；Hellenic Mediterranean University（希腊地中海大学）；University of Crete（克里特大学）
Saving the Limping: Fault-tolerant Quadruped Locomotion via Reinforcement Learning
NVIDIA AI Technology Centre (NVAITC)（英伟达人工智能技术中心（NVAITC））；School of Computer Science and Engineering, Nanyang Technological University（南洋理工大学计算机科学与工程学院）；Coventry University（考文垂大学）；Mahindra University（马恒达大学）
Multi-Task Learning of Active Fault-Tolerant Controller for Leg Failures in Quadruped robots
Academy for Engineering and Technology, Fudan University（复旦大学工程与技术学院）；Beijing Jingcheng Zhitong Robotics Technology Co.（北京京城智通机器人科技有限公司）；Ji Hua Laboratory（季华实验室）；Engineering Research Center of AI and Robotics（人工智能与机器人工程研究中心）
ZSL-RPPO: Zero-Shot Learning for Quadrupedal Locomotion in Challenging Terrains using Recurrent Proximal Policy Optimization
Huawei Technologies（华为技术有限公司）；Huawei Munich Research Center（华为慕尼黑研究中心）；University College London（伦敦大学学院）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；East China Normal University（华东师范大学）
Learning Free Gait Transition for Quadruped Robots via Phase-Guided Controller
Zhejiang University（浙江大学）；ZJU-Hangzhou Global Scientific and Technological Innovation Center（浙江大学-杭州市全球科技创新中心）；State Key Laboratory of Fluid Power and Mechatronic System, Zhejiang University（浙江大学流体动力与机电系统国家重点实验室）；Institute of Applied Mechanics, Zhejiang University（浙江大学应用力学研究所）
Learning Diverse Natural Behaviors for Enhancing the Agility of Quadrupedal Robots
Department of Control Science and Intelligent Engineering（控制科学与智能工程系）；School of Management and Engineering（管理与工程学院）；Australian Artificial Intelligence Institute（澳大利亚人工智能研究所）
An Adaptive Control Algorithm for Quadruped Locomotion with Proprioceptive Linear Legs
Shenzhen Institute of Artificial Intelligence and Robotics for Society (AIRS)（深圳人工智能与机器人研究院）；Georgia Institute of Technology（佐治亚理工学院）；Hong Kong University of Science and Technology（香港科技大学）；Southern University of Science and Technology (SUSTech)（南方科技大学）；Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
Online Trajectory Optimization for Dynamic Aerial Motions of a Quadruped Robot
Massachusetts Institute of Technology（麻省理工学院）
这项工作提出了一个两部分的框架，在线规划和执行的动态空中运动的四足机器人。运动规划通过质心动量为基础的非线性优化，是一般足以产生丰富的新的动态运动集的基础上，仅根据用户指定的接触时间表和所需的发射速度的机器人。由于这种非线性优化对于实时滚动时域控制来说是不容易处理的，因此在空中运动的准备中经由非线性优化来规划运动一次，然后使用基于变分的最优控制器来连续跟踪运动，该基于变分的最优控制器对存在于实际硬件中的不确定性（诸如建模误差或干扰）提供鲁棒性。运动规划通常需要0.05-0.15秒，而最佳控制器在500 Hz时找到稳定的反馈输入。在MIT Mini Cheetah上的实验结果表明，该框架可以可靠地产生成功的空中运动，如跳上和跳下平台、旋转、翻转、桶形滚转和跨越障碍物的跳跃。
Design and Control of the "QuadBoat": A Quadruped Surface Vehicle for Drowning Rescue
Shenzhen Institute of Artificial Intelligence and Robotics for Society (AIRS)（深圳社会人工智能与机器人研究所）；The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen)（香港中文大学（深圳））；Stevens Institute of Technology（史蒂文斯理工学院）
Adaptive Model-Base Control of Quadrupeds via Online System Identification using Kalman Filter
Robotics Innovation Center, German Research Center for Artificial Intelligence (DFKI GmbH)（机器人创新中心，德国人工智能研究中心（DFKI GmbH））；AG Robotik, University of Bremen（机器人技术研究所，不莱梅大学）；Dynamics Division, Department of Mechanics & Maritime Sciences, Chalmers University of Technology（动力学研究所，机械与海洋科学系，查尔姆斯理工大学）
