𝔖 Scriptorium
✦   LIBER   ✦

πŸ“

Robotic Computing on FPGAs (Synthesis Lectures on Distributed Computing Theory)

✍ Scribed by Shaoshan Liu, Zishen Wan, Bo Yu


Publisher
Morgan & Claypool
Year
2021
Tongue
English
Leaves
220
Series
Synthesis Lectures on Computer Architecture
Category
Library

⬇  Acquire This Volume

No coin nor oath required. For personal study only.

✦ Synopsis


This book provides a thorough overview of the state-of-the-art field-programmable gate array (FPGA)-based robotic computing accelerator designs and summarizes their adopted optimized techniques. This book consists of ten chapters, delving into the details of how FPGAs have been utilized in robotic perception, localization, planning, and multi-robot collaboration tasks. In addition to individual robotic tasks, this book provides detailed descriptions of how FPGAs have been used in robotic products, including commercial autonomous vehicles and space exploration robots.

✦ Table of Contents


Preface
Introduction and Overview
Sensing
Perception
Localization
Planning and Control
FPGAs in Robotic Applications
The Deep Processing Pipeline
Summary
FPGA Technologies
An Introduction to FPGA Technologies
Types of FPGAs
FPGA Architecture
Commercial Applications of FPGAs
Partial Reconfiguration
What is Partial Reconfiguration?
How to Use Partial Reconfiguration?
Achieving High Performance
Real-World Case Study
Robot Operating System (ROS) on FPGAs
Robot Operating System (ROS)
ROS-Compliant FPGAs
Optimizing Communication Latency for the ROS-Compliant FPGAs
Summary
Perception on FPGAs – Deep Learning
Why Choose FPGAs for Deep Learning?
Preliminary: Deep Neural Network
Design Methodology and Criteria
Hardware-Oriented Model Compression
Data Quantization
Weight Reduction
Hardware Design: Efficient Architecture
Computation Unit Designs
Loop Unrolling Strategies
System Design
Evaluation
Summary
Perception on FPGAs – Stereo Vision
Perception in Robotics
Stereo Vision in Robotics
Local Stereo Matching on FPGAs
Algorithm Framework
FPGA Designs
Global Stereo Matching on FPGAs
Algorithm Framework
FPGA Designs
Semi-Global Matching on FPGAs
Algorithm Framework
FPGA Designs
Efficient Large-Scale Stereo Matching on FPGAs
ELAS Algorithm Framework
FPGA Designs
Evaluation and Discussion
Dataset and Accuracy
Power and Performance
Summary
Localization on FPGAs
Preliminary
Context
Algorithm Overview
Algorithm Framework
Frontend FPGA Design
Overview
Exploiting Task-Level Parallelisms
Backend FPGA Design
Evaluation
Experimental Setup
Resource Consumption
Performance
Summary
Planning on FPGAs
Motion Planning Context Overview
Probabilistic Roadmap
Rapidly Exploring Random Tree
Collision Detection on FPGAs
Motion Planning Compute Time Profiling
General Purpose Processor-Based Solutions
Specialized Hardware Accelerator-Based Solutions
Evaluation and Discussion
Graph Search on FPGAs
Summary
Multi-Robot Collaboration on FPGAs
Multi-Robot Exploration
INCAME Framework for Multi-Task on FPGAs
Hardware Resource Conflicts in ROS
Interruptible Accelerator with ROS (INCAME)
Virtual Instruction-Based Accelerator Interrupt
Instruction Driven Accelerator
How to Interrupt: Virtual Instruction
Where to Interrupt: After SAVE/CALC_F
Latency Analysis
Virtual Instruction ISA (VI-ISA)
Instruction Arrangement Unit (IAU)
Example of Virtual Instruction
Evaluation and Results
Experiment Setup
Virtual Instruction-Based Interrupts
ROS-Based MR-Exploration
Summary
Autonomous Vehicles Powered by FPGAs
The PerceptIn Case Study
Design Constraints
Overview of the Vehicle
Performance Requirements
Energy and Cost Considerations
Software Pipeline
On Vehicle Processing System
Hardware Design Space Exploration
Hardware Architecture
Sensor Synchronization
Performance Characterizations
Summary
Space Robots Powered by FPGAs
Radiation Tolerance for Space Computing
Space Robotic Algorithm Acceleration on FPGAs
Feature Detection and Matching
Stereo Vision
Deep Learning
Utilization of FPGAs in Space Robotic Missions
Mars Exploration Rover Missions
Mars Science Laboratory Mission
Mars 2020 Mission
Summary
Conclusion
What we Have Covered in This Book
Looking Forward
Bibliography
Authors' Biographies
Blank Page


πŸ“œ SIMILAR VOLUMES


Introductory Tiling Theory for Computer
✍ Craig Kaplan πŸ“‚ Library πŸ“… 2009 πŸ› Morgan and Claypool Publishers 🌐 English

Tiling theory is an elegant branch of mathematics that has applications in several areas of computer science. The most immediate application area is graphics, where tiling theory has been used in the contexts of texture generation, sampling theory, remeshing, and of course the generation of decorati

Background Subtraction: Theory and Pract
✍ Ahmed Elgammal πŸ“‚ Library πŸ“… 2014 πŸ› Morgan & Claypool Publishers 🌐 English

<p>Background subtraction is a widely used concept for detection of moving objects in videos. In the last two decades there has been a lot of development in designing algorithms for background subtraction, as well as wide use of these algorithms in various important applications, such as visual surv

Metareasoning for Robots: Adapting in Dy
✍ Jeffrey W. Herrmann πŸ“‚ Library πŸ“… 2023 πŸ› Springer 🌐 English

<p><span>This book is a state of the artΒ resource that robotics researchers and engineers can use to make their robots and autonomous vehicles smarter. Readers will be able to describe metareasoning, select an appropriate metareasoning approach, and synthesize metareasoning policies.Β </span><span>Me

The Data Center as a Computer (Synthesis
✍ Luiz Barroso πŸ“‚ Library πŸ“… 2009 🌐 English

As computation continues to move into the cloud, the computing platform of interest no longer resembles a pizza box or a refrigerator, but a warehouse full of computers. These new large datacenters are quite different from traditional hosting facilities of earlier times and cannot be viewed simply a

Introduction to Reconfigurable Supercomp
✍ Marco Lanzagorta, Stephen Bique, Robert Rosenberg πŸ“‚ Library πŸ“… 2010 πŸ› Morgan and Claypool Publishers 🌐 English

This book covers technologies, applications, tools, languages, procedures, advantages, and disadvantages of reconfigurable supercomputing using Field Programmable Gate Arrays (FPGAs). The target audience is the community of users of High Performance Computers (HPC) who may benefit from porting their