Gait Generation for a Quadrupedal Robot

Abstract

Quadrupedal robots have gained significant research interest due to their ability to achieve agile and stable locomotion over complex terrains. Such locomotion can be achieved by combining various gaits, however, simply changing robot gaits does not guarantee robust and stable behavior. To ensure stable robot locomotion, gaits must be seamlessly blended. Current methods of gait transition include model-based, mainly Model Predictive Control (MPC), approaches, which are limited by the use of handengineered gaits; Reinforcement Learning (RL)-based methods, which address these limitations but require extensive training; and hybrid methods that combine multiple controllers but still experience abrupt gait timing changes. This thesis introduces a novel RL-MPC hybrid control framework that addresses the controllers’ shortcomings in the current literature. The proposed controller incorporates a feature extractor module that extracts features from the robot terrain and state. The novel framework also introduces a gait timing correction step to smooth out gait transitions. The proposed framework was tested on a randomly generated rough terrain, where the robot efficiently traversed and transitioned between gaits while maintaining accurate command velocity. Testing the effectiveness of the contact timing correction step revealed that the locomotion produced by the controller without contact timing correction was jerky and unstable on rough terrain. The proposed framework also outperforms a state-of-the-art method in gait transitioning, resulting in smoother and more stable locomotion. XIThe rest of the research has been structured as follows: Chapter 1 discusses quadrupedal robots in general, the different quadrupedal robot platforms that have been introduced over the years, and the commonly used controllers for quadrupedal robots, which include MPC, RL, hybrid controllers, and PD controllers. We discuss robot gait design, different types of robot gait transition models, and finally the shortcomings in the current literature that limit the robot’s ability to transition gaits. Chapter 2 discusses the current literature and the different controllers that are used for gait transition. The controller frameworks are shown for reference and their details and limitations are discussed. Chapter 3 focuses on the proposed framework, and the individual framework elements are discussed briefly. The role of each element is discussed and the dependence of the steps on one another is also discussed here. Chapter 4 discusses the framework from Chapter 3 in great detail. All the processes involved and their significance are elaborated. The architecture of the feature extractor, the RL policy model, and the mathematical models are also presented in this chapter. Chapter 5 elaborates on the different experiments that are planned to evaluate the proposed controllers. The results from the experiments are also discussed in this section. Chapter 6 concludes the thesis and gives a brief overview of what was achieved in this research. Different future avenues for the current research are also discussed.