• Home
  • Search
  • RoboX: An End-to-End Solution to Accelerate Autonomous Control in Robotics
  • Cite Icon35
  • https://doi.org/10.1109/isca.2018.00047Copy DOI Icon

RoboX: An End-to-End Solution to Accelerate Autonomous Control in Robotics

  • Jun 1, 2018
  • Jacob Sacks +4 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Novel algorithmic advances have paved the way for robotics to transform the dynamics of many social and enterprise applications. To achieve true autonomy, robots need to continuously process and interact with their environment through computationally-intensive motion planning and control algorithms under a low power budget. Specialized architectures offer a potent choice to provide low-power, high-performance accelerators for these algorithms. Instead of taking a traditional route which profiles and maps hot code regions to accelerators, this paper delves into the algorithmic characteristics of the application domain. We observe that many motion planning and control algorithms are formulated as a constrained optimization problems solved online through Model Predictive Control (MPC). While models and objective functions differ between robotic systems and tasks, the structure of the optimization problem and solver remain fixed. Using this theoretical insight, we create RoboX, an end-to-end solution which exposes a high-level domain-specific language to roboticists. This interface allows roboticists to express the physics of the robot and its task in a form close to its concise mathematical expressions. The RoboX backend then automatically maps this high-level specification to a novel programmable architecture, which harbors a programmable memory access engine and compute-enabled interconnects. Hops in the interconnect are augmented with simple functional units that either operate on in-fight data or are bypassed according a micro-program. Evaluations with six different robotic systems and tasks show that RoboX provides a 29.4X (7.3X) speedup and 22.1X (79.4X) performance-per-watt improvement over an ARM Cortex A57 (Intel Xeon E3). Compared to GPUs, RoboX attains 7.8X, 65.5X, and 71.×8 higher Performance-per-Watt to Tegra X2, GTX 650 Ti, and Tesla K40 with a power envelope of only 3.4 Watts at 45 nm.

Similar Papers
  • Research Article
  • Citations17

Interleaved Predictive Control and Planning for an Unmanned Aerial Manipulator With on-the-Fly Rapid Re-Planning in Unknown Environments

  • Jul 01, 2023
  • IEEE Transactions on Automation Science and Engineering
  • Mohammadreza Yavari +2
  • Conference Article
  • Citations13

Method for applying reinforcement learning to motion planning and control of under-actuated underwater vehicle in unknown non-uniform sea flow

  • Jan 01, 2005
  • H Kawano
  • Conference Article
  • Citations14

A Review of Path Planning and Control for Autonomous Robots

  • Nov 01, 2018
  • Byron Hernandez +1
  • Conference Article
  • Citations11

Development of a reduced size unmanned car

  • Mar 01, 2008
  • E Bertolazzi +5
  • Conference Article
  • Citations1

Ground Micro-Gravity Experiment System for Space Robot with Free-Floating Satellite Base

  • Nov 06, 2020
  • Jiayuan Lu +2
  • Research Article
  • Citations4

Hierarchical coordination control of mobile robots

  • Jan 01, 2012
  • Data Archiving and Networked Services (DANS)
  • Sisdarmanto Adinandra
  • Book Chapter
  • Citations48

Safe Motion Planning for Imprecise Robotic Manipulators by Minimizing Probability of Collision

  • Jan 01, 2016
  • Wen Sun +3
  • Conference Article
  • Citations18

NavDog

  • Mar 22, 2021
  • Liyang Wang +2
  • Research Article
  • Citations27

Coordination for Connected and Autonomous Vehicles at Unsignalized Intersections: An Iterative Learning-Based Collision-Free Motion Planning Method

  • Feb 01, 2024
  • IEEE Internet of Things Journal
  • Bowen Wang +4
  • Conference Article
  • Citations34

Toward Interactive Reaching in Static Environments for Humanoid Robots

  • Oct 01, 2006
  • Evan Drumwright +1
  • Research Article
  • Citations10

Motion planning for automated construction

  • May 01, 1994
  • Automation in Construction
  • Raghavan Kunigahalli +2
  • Research Article
  • Citations2

Cognitive response navigation algorithm for mobile robots using biological antennas

  • Dec 03, 2013
  • Robotica
  • Jiliang Jiang +3
  • Research Article
  • Citations4

Informed Sampling-Based Motion Planning for Manipulating Multiple Micro Agents Using Global External Electric Fields

  • Jul 01, 2022
  • IEEE Transactions on Automation Science and Engineering
  • Xilin Li +3
  • Research Article
  • Citations86

Real-time NURBS interpolation using FPGA for high speed motion control

  • Aug 01, 2006
  • Computer-Aided Design
  • Hong-Tzong Yau +2
  • Conference Article
  • Citations3

Research on Strategy and Algorithm of Lateral Motion Control for Autonomous Driving Electric Vehicle

  • Sep 01, 2019
  • Jian Zhong +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.