Visual-Inertial Odometry on Chip: An Algorithm-and-Hardware Co-design Approach

Abstract

Abstract-Autonomous navigation of miniaturized robots (e.g., nano/pico aerial vehicles) is currently a grand challenge for robotics research, due to the need for processing a large amount of sensor data (e.g., camera frames) with limited on-board computational resources. In this paper we focus on the design of a visual-inertial odometry (VIO) system in which the robot estimates its ego-motion (and a landmark-based map) from onboard camera and IMU data. We argue that scaling down VIO to miniaturized platforms (without sacrificing performance) requires a paradigm shift in the design of perception algorithms, and we advocate a co-design approach in which algorithmic and hardware design choices are tightly coupled. Our contribution is four-fold. First, we discuss the VIO co-design problem, in which one tries to attain a desired resource-performance trade-off, by making suitable design choices (in terms of hardware, algorithms, implementation, and parameters). Second, we characterize the design space, by discussing how a relevant set of design choices affects the resource-performance trade-off in VIO. Third, we provide a systematic experiment-driven way to explore the design space, towards a design that meets the desired trade-off. Fourth, we demonstrate the result of the co-design process by providing a VIO implementation on specialized hardware and showing that such implementation has the same accuracy and speed of a desktop implementation, while requiring a fraction of the power.

Visual-Inertial Navigation: A Concise Review

“…• Persistent localization: While current VINS are able to provide accurate 3D motion tracking, but, in smallscale friendly environments, they are not robust enough for long-term, large-scale, safety-critical deployments, e.g., autonomous driving, in part due to resource constraints [95,97,164]. As such, it is demanding to enable persistent VINS even in challenging conditions (such as bad lighting and motions), e.g., by efficiently integrating loop closures or building and utilizing novel maps.…”

Robot Co-design: Beyond the Monotone Case

“…For the design space of the "computation", we actually considered the joint selection of the computing board and the visual-inertial navigation (VIN) algorithm used for state estimation. Considering them as a single component has the advantage of allowing the use of statistics reported in other papers, e.g., stating that a VIN algorithm runs at a given framerate on a given computer [1]. Therefore our modules are M .…”

“…Recent advances in sensor design and rapid prototyping are enabling the manufacturing of low-cost robots with advanced sensing and perception capabilities. For instance, one can implement high-precision visual-inertial navigation with inexpensive camera and MEMS inertial measurement units [1]. Similarly, modern embedded CPU-GPU [2] offer high-performance computing in a compact form-factor and at a relatively affordable cost.…”

“…IV. Drone design is an interesting topic per se, and has already received attention in the literature [16], [1], which however still lacks a computational design approach. New and untapped challenges arise in the codesign of multi-robot systems.…”

Good Feature Matching: Toward Accurate, Robust VO/VSLAM With Low Latency

“…1, right). Exploring the co-design space between VO (with inertial) algorithm and hardware illuminates parametric settings that improve VO output [11]. Building more efficient VO/VSLAM algorithms, in parallel with better hardware integration, is important to realizing the goal of accurate, low-latency VSLAM.…”