Absolute Pose Estimation for a Millimeter-Scale Vision System

Vision is an important component of robotic perception systems due to the rich information provided by high resolution image sensors, but computer vision algorithms can be computationally expensive and ill-suited to resource-constrained robotic systems. Here, we present a mm-scale vision system capable of performing absolute pose estimation at 16. 5 FPS. This novel vision system uses a commercial-off-the-shelf sensor and microcontroller unit, as well as planar light-based landmarks in the environment to simplify feature detection. We exploit the structure of the planar pose problem to reduce algorithmic complexity and improve latency and energy consumption through software-, processor-, and hardware-in-the-loop testing. The end-to-end system consumes 49 mA of current and computes absolute pose estimates within 15 mm over a number of reference trajectories.

Authors

• Derin Ozturk
• Zilin Wang
• E. Farrell Helbling

Keywords

• Energy consumption
• Microcontrollers
• Machine vision
• Feature detection
• Pose estimation
• Robot sensing systems
• Hardware
• Motion capture
• Trajectory
• Testing
• Visual System
• Absolute Estimates
• Absolute Pose
• Absolute Pose Estimation
• Singular Value Decomposition
• Current Consumption
• Image Coordinates
• Camera Pose
• Logical Analysis
• Gram Matrix
• Number Of Rotations
• Images In Row
• Flash Memory
• End Of Frame
• Improvement In Cases
• Landmark Detection
• Number Of Landmarks
• Serial Peripheral Interface
• Micro Air Vehicles
• Experimental Loop
• Improvement In Latency
• Pairs Of Columns
• Camera Module
• Ground Plane
• Frame Rate
• Reduction In The Number
• Linear System