We propose a reinforcement learning-based framework for co-optimization and demonstrate successful optimization, construction, and zero-shot sim-to-real transfer of several soft crawling robots. In this work, we show that finite element simulation combined with recent model order reduction techniques provide both the efficiency and the accuracy required to successfully learn effective soft robot design-control pairs that transfer to reality. However, the complex nature of soft robot dynamics makes it difficult to provide a simulation environment that is both sufficiently accurate to allow for sim-to-real transfer, while also being fast enough for contemporary co-optimization algorithms. Co-optimization provides a promising means to generate sophisticated soft robots by reasoning over this coupling. Exploiting this capacity requires careful consideration of the coupling between mechanical design and control. The compliance of soft robots provides a form of "mechanical intelligence" - the ability to passively exhibit behaviors that would otherwise be difficult to program. This work provides a complete framework for the simulation, co-optimization, and sim-to-real transfer of the design and control of soft legged robots. Finally, we conclude by exploring the fabrication and deployment of optimized soft robots. We then follow this up with an extension to allow for the optimization over discrete morphological parameters such as the number and configuration of limbs. Our approach efficiently optimizes both physical design and control parameters directly for task performance by leveraging a design-conditioned controller capable of generalizing over the space of physical designs. In our work, we start by proposing a data-efficient algorithm based on multi-task reinforcement learning. We then turn our attention to the related problem of task-driven optimization of robots and their controllers. In our work, we develop a deep learning approach to optimize both beacon placement and location inference directly for localization accuracy. Designing such a system involves placing beacons throughout the environment and inferring location from sensor readings. We start by considering the problem of optimizing a beacon-based localization system directly for localization accuracy. This thesis explores work on the task-driven co-optimization of robotics systems in an end-to-end manner, simultaneously optimizing the physical components of the system with inference or control algorithms directly for task performance. Therefore, it is often necessary to consider the interactions between these components when designing an embodied system. The ability of these systems to complete these tasks depends on a large range of technologies such as the mechanical and electrical parts that make up the physical body of the robot and its sensors, perception algorithms to perceive the environment, and planning and control algorithms to produce meaningful actions. Robots and intelligent systems that sense or interact with the world are increasingly being used to automate a wide array of tasks.
0 kommentar(er)
