Title
Visual Perception for Humanoid Robots: Environmental Recognition and Localization, from Sensor Signals to Reliable 6D Poses (Cog,Used
Sold by Ergodebooks, an authorized reseller.
Returns accepted within 30 days | support@ergodebooks.com
Shipping Information
- Free Standard Shipping — United States only
- Processing Time: 1–3 business days
- Estimated Delivery: 3–5 business days after dispatch
- Double-boxed, fully insured & discreetly packaged
- Tracking number sent via email once dispatched
- Orders over $250 require signature upon delivery. Taxes calculated at checkout.
Returns & Refund
Returns accepted within 30 days of delivery.
Damaged or Defective Item
Free return shipping + replacement or full refund
Wrong Item Received
Free return shipping + replacement or full refund
Change of Mind
Return shipping at customer's expense · 25% restocking fee applies
Payment Option
This book provides an overview of modelbased environmental visual perception for humanoid robots. The visual perception of a humanoid robot creates a bidirectional bridge connecting sensor signals with internal representations of environmental objects. The objective of such perception systems is to answer two fundamental questions: What & where is it? To answer these questions using a sensortorepresentation bridge, coordinated processes are conducted to extract and exploit cues matching robots mental representations to physical entities. These include sensor & actuator modeling, calibration, filtering, and feature extraction for state estimation. This book discusses the following topics in depth: Active Sensing: Robust probabilistic methods for optimal, high dynamic range image acquisition are suitable for use with inexpensive cameras. This enables ideal sensing in arbitrary environmental conditions encountered in humancentric spaces. The book quantitatively shows the importance of equipping robots with dependable visual sensing. Feature Extraction & Recognition: Parameterfree, edge extraction methods based on structural graphs enable the representation of geometric primitives effectively and efficiently. This is done by eccentricity segmentation providing excellent recognition even on noisy & lowresolution images. Stereoscopic vision, Euclidean metric and graphshape descriptors are shown to be powerful mechanisms for difficult recognition tasks. Global SelfLocalization & Depth Uncertainty Learning: Simultaneous feature matching for global localization and 6D selfpose estimation are addressed by a novel geometric and probabilistic concept using intersection of Gaussian spheres. The path from intuition to the closedform optimal solution determining the robot location is described, including a supervised learning method for uncertainty depth modeling based on extensive groundtruth training data from a motion capture system.The methods and experiments are presented in selfcontained chapters with comparisons and the state of the art. The algorithms were implemented and empirically evaluated on two humanoid robots: ARMAR IIIA & B. The excellent robustness, performance and derived results received an award at the IEEE conference on humanoid robots and the contributions have been utilized for numerous visual manipulation tasks with demonstration at distinguished venues such as ICRA, CeBIT, IAS, and Automatica.
⚠️ WARNING (California Proposition 65):
This product may contain chemicals known to the State of California to cause cancer, birth defects, or other reproductive harm.
For more information, please visit www.P65Warnings.ca.gov.