Legged animals possess extraordinary agility with which they can gracefully traverse a wide range of environments, from running through grasslands to jumping across cliffs and climbing nearly vertical walls. Inspired by this, in this work, we use Deep Reinforcement Learning to give legged robots the ability to perform a diverse set of highly explosive and agile jumps. Unlike other works, our approach is not constrained to imitating a reference trajectory. We instead use curriculum-based learning to progressively learn more challenging tasks, starting from a vertical high jump and then generalising to forward and diagonal jumps. In the final curriculum stage, the robot learns to leap over barrier-like obstacles or to land on them, conditioned on the desired jumping distance and the object's dimensions. We show that such an approach can produce a wide range of robust and precise motions, which we thoroughly and successfully validated in several indoor and outdoor real-world experiments on the Unitree Go1 robot. In our real-world experiments, we show a forward jump of 90cm, exceeding previous records for similar robots reported in the literature. Additionally, we investigate the effects of incorporating bio-inspired parallel elastic actuators to improve the jumping performance further. This resulted in smoother motions, much softer landings with lower joint velocities and larger jumps. Finally, we present and analyse the limitations of our method and introduce exciting directions for future work to address them.

In this thesis, we introduce a novel approach aimed at enhancing the jumping and landing capabilities of quadruped robots. Our method integrates both model-based and model-free strategies and features a behavioral cloning framework designed to reduce computational delays often encountered in trajectory optimization. Initially, we build upon an existing framework for quadruped jumps, where we refine the trajectory optimization (TO) algorithm and introduce a new Variable Impedance Control (VIC). The VIC is specifically developed to facilitate softer landings. This improved system was then utilized to generate a comprehensive synthetic dataset, including 11,000 samples that cover a diverse range of jumping scenarios. This dataset served as the foundation for training a neural network. The primary objective of the network is to emulate the performance of the model-based approach. Structurally, the network is designed to process the robot's current state as input and generate the corresponding control actions for its 12 motors as output. The most significant achievement of this research is the neural network's ability to closely replicate the outcomes of the model-based solution. Notably, it ensures more compliant behavior and lower stress on the motors during the landing phase than an MPC. The neural network demonstrates a 97.4% success rate. This high level of performance underscores its potential for on-the-fly application in robotic systems. The effectiveness of our method is further validated through a series of simulations and practical tests conducted on a Go1 quadruped robot.

Effectively controlling and exploiting the natural dynamics of Articulated Soft Robots for energy-efficient motions remains challenging. In literature, the problem is often split in two; in energy-efficient motion planning and structure-preserving control, where the focus is on one, and the other is largely disregarded. This work aims to unify these two using a motion planning and control strategy based on trajectory optimization and functional Iterative Learning Control. Using a reduced-order model, the planner generates an energy-efficient reference trajectory by minimizing the Cost of Transport. The controller then iteratively learns the feedforward control signal such that the full-order system tracks the reference, without altering its stiffness characteristics. We show that our strategy results in energy-efficient tracking of the reference. We also show how functional Iterative Learning Control can be used in a continuous approach to learn a stable forward pronking gait. We give experimental validation of this approach through experiments on the compliant quadruped E-Go. We show that the pronking gait can be learned on hardware in minutes and that it is robust to various types of terrain.