Controlling Robot Morphology From Incomplete Measurements

Pecka, Martin; Zimmermann, Karel; Michal, R.; Svoboda, Tomáš

doi:10.1109/tie.2016.2580125

Cited by 15 publications

(10 citation statements)

References 31 publications

(62 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar to our approach, Pecka, Zimmermann, Reinstein, and Svoboda (2017) show a tracked platform that is able to compensate incomplete laser sensor measurements with a robotic arm, e.g., below water surfaces. However, the approach is only used to compensate for incomplete sensor measurements.…”

Section: Locomotion In Challenging Terrainmentioning

confidence: 99%

Weaver: Hexapod robot for autonomous navigation on unstructured terrain

Bjelonic

Kottege

Homberger

et al. 2018

Journal of Field Robotics

View full text Add to dashboard Cite

Legged robots are an efficient alternative for navigation in challenging terrain. In this paper we describe Weaver, a six‐legged robot that is designed to perform autonomous navigation in unstructured terrain. It uses stereo vision and proprioceptive sensing based terrain perception for adaptive control while using visual‐inertial odometry for autonomous waypoint‐based navigation. Terrain perception generates a minimal representation of the traversed environment in terms of roughness and step height. This reduces the complexity of the terrain model significantly, enabling the robot to feed back information about the environment into its controller. Furthermore, we combine exteroceptive and proprioceptive sensing to enhance the terrain perception capabilities, especially in situations in which the stereo camera is not able to generate an accurate representation of the environment. The adaptation approach described also exploits the unique properties of legged robots by adapting the virtual stiffness, stride frequency, and stride height. Weaver's unique leg design with five joints per leg improves locomotion on high gradient slopes, and this novel configuration is further analyzed. Using these approaches, we present an experimental evaluation of this fully self‐contained hexapod performing autonomous navigation on a multiterrain testbed and in outdoor terrain.

show abstract

Section: Locomotion In Challenging Terrainmentioning

confidence: 99%

Weaver: Hexapod robot for autonomous navigation on unstructured terrain

Bjelonic

Kottege

Homberger

et al. 2018

Journal of Field Robotics

View full text Add to dashboard Cite

show abstract

“…Fanuc [11], the world's largest maker of industrial robots, has used RL methods to train robots to precisely pick up a box and put it in a container. In the automotive industry, authors in [16] have proposed an RLbased approach to control robot morphology (flippers) to move over rough terrains that exist in Urban Search and Rescue missions.…”

Section: Background and Related Workmentioning

confidence: 99%

OPEB: Open physical environment benchmark for artificial intelligence

Mirzaei

Fathollahi

Givargis

2017

2017 IEEE 3rd International Forum on Research and Technologies for Society and Industry (RTSI)

View full text Add to dashboard Cite

Artificial Intelligence methods to solve continuouscontrol tasks have made significant progress in recent years. However, these algorithms have important limitations and still need significant improvement to be used in industry and realworld applications. This means that this area is still in an active research phase. To involve a large number of research groups, standard benchmarks are needed to evaluate and compare proposed algorithms. In this paper, we propose a physical environment benchmark framework to facilitate collaborative research in this area by enabling different research groups to integrate their designed benchmarks in a unified cloud-based repository and also share their actual implemented benchmarks via the cloud. We demonstrate the proposed framework using an actual implementation of the classical mountain-car example and present the results obtained using a Reinforcement Learning algorithm.

show abstract

“…A CCURATE real-time prediction of robot-terrain interaction from raw sensory measurements is crucial for many mobile robotic tasks ranging from computing traversability/costmap for high-level path planning [1] to state representation for low-level motion control [2]. Even though a usual lowlevel map such as ICP-aligned lidar scans (optionally discretized to voxelmap or heightmap) is often sparse and assumes terrain to be rigid, it is often used as an input to these tasks [1], [3]- [6].…”

Section: Introductionmentioning

confidence: 99%

Pose Consistency KKT-Loss for Weakly Supervised Learning of Robot-Terrain Interaction Model

Šalanský

Zimmermann

Petříček

et al. 2021

IEEE Robot. Autom. Lett.

Self Cite

View full text Add to dashboard Cite

We address the problem of self-supervised learning for predicting the shape of supporting terrain (i.e. the terrain which will provide rigid support for the robot during its traversal) from sparse input measurements. The learning method exploits two types of ground-truth labels: dense 2.5D maps and robot poses, both estimated by a usual SLAM procedure from offline recorded measurements. We show that robot poses are required because straightforward supervised learning from the 3D maps only suffers from: (i) exaggerated height of the supporting terrain caused by terrain flexibility (vegetation, shallow water, snow or sand) and (ii) missing or noisy measurements caused by high spectral absorbance or non-Lambertian reflectance of the measured surface. We address the learning from robot poses by introducing a novel KKT-loss, which emerges as the distance from necessary Karush-Kuhn-Tucker conditions for constrained local optima of a simplified first-principle model of the robot-terrain interaction. We experimentally verify that the proposed weakly supervised learning from ground-truth robot poses boosts the accuracy of predicted support heightmaps and increases the accuracy of estimated robot poses. All experiments are conducted on a dataset captured by a real platform. Both the dataset and codes which replicates experiments in the paper are made publicly available as a part of the submission.

show abstract

Controlling Robot Morphology From Incomplete Measurements

Cited by 15 publications

References 31 publications

Weaver: Hexapod robot for autonomous navigation on unstructured terrain

Weaver: Hexapod robot for autonomous navigation on unstructured terrain

OPEB: Open physical environment benchmark for artificial intelligence

Pose Consistency KKT-Loss for Weakly Supervised Learning of Robot-Terrain Interaction Model

Contact Info

Product

Resources

About