An Energy-Efficient and Runtime-Reconfigurable FPGA-Based Accelerator for Robotic Localization Systems
Authors:
Preprint
Abstract
Simultaneous Localization and Mapping (SLAM) estimates agents' trajectories and constructs maps, and localization is a fundamental kernel in autonomous machines at all computing scales, from drones, AR, VR to self-driving cars. In this work, we present an energy-efficient and runtime-reconfigurable FPGA-based accelerator for robotic localization. We exploit SLAM-specific data locality, sparsity, reuse, and parallelism, and achieve >5x performance improvement over the state-of-the-art. Especially, our design is reconfigurable at runtime according to the environment to save power while sustaining accuracy and performance.Keywords
All Related Versions
This publication has 4 references indexed in Scilit:
- Eudoxus: Characterizing and Accelerating Localization in Autonomous Machines Industry Track Paper2021
- π-BA: Bundle Adjustment Hardware Accelerator based on Distribution of 3D-Point ObservationsIEEE Transactions on Computers, 2020
- An 879GOPS 243mW 80fps VGA Fully Visual CNN-SLAM Processor for Wide-Range Autonomous Exploration2019
- Visual-Inertial Odometry on Chip: An Algorithm-and-Hardware Co-design Approach2017