Abstract-- In this paper, we address the problem of real-time motion planning for multiple robotic manipulators that operate in close proximity. We build upon the concept of dynamic fabrics and extend them to multi-robot systems, referred to as Multi-Robot Dynamic Fabrics (MRDF). This geometric method enables a very high planning frequency for high-dimensional systems at the expense of being reactive and prone to deadlocks. To detect and resolve deadlocks, we propose Rollout Fabrics where MRDF are forward simulated in a decentralized manner. Franka Emika Pandas pick cubes avoiding collisions.

Abstract--Optimization fabrics are a geometric approach to realtime local motion generation, where motions are designed by the composition of several differential equations that exhibit a desired motion behavior. We generalize this framework to dynamic scenarios and non-holonomic robots and prove that fundamental properties can be conserved. We show that convergence to desired trajectories and avoidance of moving obstacles can be guaranteed using simple construction rules of the components. The open-source implementation can be found at https://github. Imagine physical limits and obstacle avoidance. It applications of such optimization-based approaches to mobile is requested to perform different tasks, such as cleaning the robots, the computational costs limit applicability when dealing floor or picking a wide range of products. Datadriven manipulation tasks may vary in their dimension and accuracy approaches to speed up the optimization process usually requirements, e.g. Thus, it is important for motion planning algorithms to Moreover, due to the scalar objective function, the user must support various goal definitions. Further, the robot is operating carefully weigh up different parts of the objective function. As alongside humans, it has to constantly react to the changing a consequence, optimization-based approaches are challenging environment and consequently update an initial plan. As to tune and inflexible to generic motion planning problems customers move fast, the adaptations must be computed in real with variable goal objectives [6, 7]. Therefore, motion planning is often divided into global motion planning [1] and local motion planning, which we will In the field of geometric control, namely Riemannian motion refer to as motion generation in this paper.

In this paper, we present an automated parameter optimization method for trajectory generation. We formulate parameter optimization as a constrained optimization problem that can be effectively solved using Bayesian optimization. While the approach is generic to any trajectory generation method, we showcase it using optimization fabrics. Optimization fabrics are a geometric trajectory generation method based on non-Riemannian geometry. By symbolically pre-solving the structure of the tree of fabrics, we obtain a parameterized trajectory generator, called symbolic fabrics. We show that autotuned symbolic fabrics reach expert-level performance in a few trials. Additionally, we show that tuning transfers across different robots, motion planning problems and between simulation and real world. Finally, we qualitatively showcase that the framework could be used for coupled mobile manipulation.