Uploaded May 2018 | Updated September 2026, 2 weeks ago
ICRA 2018 Spotlight Video
Interactive Session Wed PM Pod H.6
Authors: Zhang, Wuming; Hauser, Kris
Title: Single-Image Footstep Prediction for Versatile Legged Locomotion
Abstract:
Walking and climbing robots need to plan long-term routes on both horizontal and vertical terrain, but on-board sensors take images from vantage points that provide strongly foreshortened images that cause the appearance of terrain features to vary greatly by distance and viewing angle. This paper presents a convolutional neural network (CNN) method for predicting valid handhold and foothold locations from single RGB+D images taken at arbitrary tilt angles. Experiments show that the method predicts holds more accurately than comparable learning techniques, and that a route planner based on these predictions generates plausible plans for flat ground, stairs, and walls in rock climbing gyms.
ICRA 2018 Spotlight Video
Interactive Session Wed PM Pod H.6
Authors: Zhang, Wuming; Hauser, Kris
Title: Single-Image Footstep Prediction for Versatile Legged Locomotion
Abstract:
Walking and climbing robots need to plan long-term routes on both horizontal and vertical terrain, but on-board sensors take images from vantage points that provide strongly foreshortened images that cause the appearance of terrain features to vary greatly by distance and viewing angle. This paper presents a convolutional neural network (CNN) method for predicting valid handhold and foothold locations from single RGB+D images taken at arbitrary tilt angles. Experiments show that the method predicts holds more accurately than comparable learning techniques, and that a route planner based on these predictions generates plausible plans for flat ground, stairs, and walls in rock climbing gyms.
