Computational co-optimization of design parameters and motion trajectories for robotic systems

Abstract

We present a novel computational approach to optimizing the morphological design of robots. Our framework takes as input a parameterized robot design as well as a motion plan consisting of trajectories for end-effectors and, optionally, for its body. The algorithm optimizes the design parameters including link lengths and actuator placements whereas concurrently adjusting motion parameters such as joint trajectories, actuator inputs, and contact forces. Our key insight is that the complex relationship between design and motion parameters can be established via sensitivity analysis if the robot's movements are modeled as spatiotemporal solutions to an optimal control problem. This relationship between form and function allows us to automatically optimize the robot design based on specifications expressed as a function of actuator forces or trajectories. We evaluate our model by computationally optimizing four simulated robots that employ linear actuators, four-bar linkages, or rotary servos. We further validate our framework by optimizing the design of two small quadruped robots and testing their performances using hardware implementations.

Remote Evaluation System of Tennis Batting Action Standard Based on Acceleration Sensor

“…rough the questionnaire survey, the tennis players' scoring criteria are set up [31,32]. e content of the questionnaire is divided into two parts: the first part is "evaluation indicators.…”

Kinematic Synthesis of a Serial Robotic Manipulator by Using Generalized Differential Inverse Kinematics

“…The twists representing three joints were then optimized, and we obtained the following twists: . (21) In this case, the sum of the squared differences was less than that in the previous case by one order of magnitude; it was e = 3.07×10 −6 [J.s].…”

“…In addition, a computation method has been proposed for the kinematic synthesis and design of a manipulator based on its dynamics [19], [20]. By considering the dynamics of the system, Ha et al [21] proposed a flexible computational approach to optimize the design of the open-and closed-loop robots with the motion trajectory itself by considering the trajectory as the design parameter and using the implicit function theorem.…”

Reinforcement Learning for Improving Agent Design

“…Recent works in robotics investigate simultaneously optimizing body design and control of a legged robot [29,30] using constraint-based modeling, which is related to our RL-based approach. Related to our work, [1,24] employ CMA-ES [31] to optimize over both the motion control and physical configuration of agents.…”