Bipedal Robot Gait Generation Using Bessel Interpolation

This paper introduces a novel approach to bipedal robot gait generation by proposing a higher-order form through the parameter equation of first-order Bessel interpolation. The trajectory planning for the bipedal robot, specifically for stepping up or down stairs, is established based on a three-dimensional interpolation equation. The experimental prototype, Roban, is utilized for the study, and the structural sketch of a single leg is presented. The inverse kinematics expression for the leg is derived using kinematic methods. Employing a position control method, the angle information is transmitted to the robot's joints, enabling the completion of both downstairs simulation experiments and physical experiments with the Roban prototype. The analysis of the experimental process reveals a noticeable phenomenon of hip and ankle joint tilting in the robot. This observation suggests that low-cost bipedal robots driven by servo motors exhibit low stiffness characteristics in their joints.

Comparative performance of machine learning models for the classification of human gait

The efficacy of human activity recognition (HAR) models mostly relies on the characteristics derived from domain expertise. The input of the classification algorithm consists of many characteristics that are utilized to accurately and effectively classify human physical activities. In contemporary research, machine learning techniques have been increasingly employed to automatically extract characteristics from unprocessed sensory input to develop models for Human Activity Recognition (HAR) and classify various activities. The primary objective of this research is to compare and contrast several machine learning models and determine a reliable and precise classification model for classifying activities. This study does a comparison analysis in order to assess the efficacy of 10 distinct machine learning models using frequently used datasets in the field of HAR. In this work, three benchmark public human walking datasets are being used. The research is conducted based on eight evaluating parameters. Based on the study conducted, it was seen that the machine learning classification models Random Forest, Extra Tree, and Light Gradient Boosting Machine had superior performance in all the eight evaluating parameters compared to specific datasets. Consequently, it can be inferred that machine learning significantly enhances performance within the area of Human Activity Recognition (HAR). This study can be utilized to provide suitable model selection for HAR-based datasets. Furthermore, this research can be utilized to facilitate the identification of various walking patterns for bipedal robotic systems.

A Multi-Agent Reinforcement Learning Method for Omnidirectional Walking of Bipedal Robots

Achieving omnidirectional walking for bipedal robots is considered one of the most challenging tasks in robotics technology. Reinforcement learning (RL) methods have proved effective in bipedal walking tasks. However, most existing methods use state machines to switch between multiple policies and achieve omnidirectional gait, which results in shaking during the policy switching process for bipedal robots. To achieve a seamless transition between omnidirectional gait and transient motion for full-size bipedal robots, we propose a novel multi-agent RL method. Firstly, a multi-agent RL algorithm based on the actor-critic framework is designed, and policy entropy is introduced to improve exploration efficiency. By learning agents with parallel initial state distributions, we minimize reliance on gait planner effectiveness in the Robot Operating System (ROS). Additionally, we design a novel heterogeneous policy experience replay mechanism based on Euclidean distance. Secondly, considering the periodicity of bipedal robot walking, we develop a new periodic gait function. Including periodic objectives in the policy can accelerate the convergence speed of training periodic gait functions. Finally, to enhance the robustness of the policy, we construct a novel curriculum learning method by discretizing Gaussian distribution and incorporate it into the robot's training task. Our method is validated in a simulation environment, and the results show that our method can achieve multiple gaits through a policy network and achieve smooth transitions between different gaits.

Research on Vibration Control Technology of Robot Motion Based on Magnetorheological Elastomer

The vibration and impact of a humanoid bipedal robot during movements such as walking, running and jumping may cause potential damage to the robot's mechanical joints and electrical systems. In this paper, a composite bidirectional vibration isolator based on magnetorheological elastomer (MRE) is designed for the cushioning and damping of a humanoid bipedal robot under foot contact forces. In addition, the vibration isolation performance of the vibration isolator was tested experimentally, and then, a vibration isolator dynamics model was developed. For the bipedal robot foot impact, based on the vibration isolator model, three vibration reduction control algorithms are simulated, and the results show that the vibration damping effect can reach 85%. Finally, the MRE vibration isolator hardware-in-the-loop-simulation experiment platform based on dSPACE has been built to verify the vibration reduction control effect of the fuzzy PID algorithm. The result shows the vibration amplitude attenuates significantly, and this verifies the effectiveness of the fuzzy PID damping control algorithm.