Dadu-RBD: Robot Rigid Body Dynamics Accelerator with Multifunctional Pipelines

TL;DR

This paper introduces RBDCore, a multifunctional FPGA-based accelerator for robot rigid body dynamics, significantly enhancing real-time computation efficiency in robotics applications like trajectory optimization.

Contribution

We present RBDCore, a hardware-optimized, multifunctional FPGA accelerator that reuses modules and dynamically switches dataflows for improved performance in robot dynamics calculations.

Findings

RBDCore outperforms CPUs and GPUs in dynamics computation speed.

It can adapt to different robot structures with structure-adaptive pipelines.

Significantly reduces computation time compared to FPGA, CPU, and GPU solutions.

Abstract

Rigid body dynamics is a key technology in the robotics field. In trajectory optimization and model predictive control algorithms, there are usually a large number of rigid body dynamics computing tasks. Using CPUs to process these tasks consumes a lot of time, which will affect the real-time performance of robots. To this end, we propose a multifunctional robot rigid body dynamics accelerator, named RBDCore, to address the performance bottleneck. By analyzing different functions commonly used in robot dynamics calculations, we summarize their reuse relationship and optimize them according to the hardware. Based on this, RBDCore can fully reuse common hardware modules when processing different computing tasks. By dynamically switching the dataflow path, RBDCore can accelerate various dynamics functions without reconfiguring the hardware. We design Structure-Adaptive Pipelines for RBDCore, which can greatly improve the throughput of the accelerator. Robots with different structures and parameters can be optimized specifically. Compared with the state-of-the-art CPU, GPU dynamics libraries and FPGA accelerator, RBDCore can significantly improve the performance.