Engineering PapersSearch

Engineering topics

Hebert, M.

Publications and source records attributed to Hebert, M..

A reactive system for open terrain navigation: Performance and limitations

We describe a core system for autonomous navigation in outdoor natural terrain. The system consists of three parts: a perception module which processes range images to identify untraversable regions of the terrain, a local map management module which maintains a representation of the environment in the vicinity of the vehicle, and a planning module which issues commands to the vehicle controller. Our approach is to use the concept of 'early traversability evaluation', and on the use of reactive planning for generating commands to drive the vehicle. We argue that our approach leads to a robust and efficient navigation system. We illustrate our approach by an experiment in which a vehicle travelled autonomously for one kilometer through unmapped cross-country terrain.

Langer, D.

A perception and manipulation system for collecting rock samples

An important part of a planetary exploration mission is to collect and analyze surface samples. As part of the Carnegie Mellon University Ambler Project, researchers are investigating techniques for collecting samples using a robot arm and a range sensor. The aim of this work is to make the sample collection operation fully autonomous. Described here are the components of the experimental system, including a perception module that extracts objects of interest from range images and produces models of their shapes, and a manipulation module that enables the system to pick up the objects identified by the perception module. The system was tested on a small testbed using natural terrain.

Choi, T.

Energy functions for regularization algorithms

Regularization techniques are widely used for inverse problem solving in computer vision such as surface reconstruction, edge detection, or optical flow estimation. Energy functions used for regularization algorithms measure how smooth a curve or surface is, and to render acceptable solutions these energies must verify certain properties such as invariance with Euclidean transformations or invariance with parameterization. The notion of smoothness energy is extended here to the notion of a differential stabilizer, and it is shown that to void the systematic underestimation of undercurvature for planar curve fitting, it is necessary that circles be the curves of maximum smoothness. A set of stabilizers is proposed that meet this condition as well as invariance with rotation and parameterization.

Delingette, H.

First results in terrain mapping for a roving planetary explorer

To perform planetary exploration without human supervision, a complete autonomous rover must be able to model its environment while exploring its surroundings. Researchers present a new algorithm to construct a geometric terrain representation from a single range image. The form of the representation is an elevation map that includes uncertainty, unknown areas, and local features. By virtue of working in spherical-polar space, the algorithm is independent of the desired map resolution and the orientation of the sensor, unlike other algorithms that work in Cartesian space. They also describe new methods to evaluate regions of the constructed elevation maps to support legged locomotion over rough terrain.

Krotkov, E.

Terrain mapping for a roving planetary explorer

A prototype legged vehicle is being developed for an exploratory mission on another planet, conceivably Mars, where it is to traverse uncharted areas and collect material samples. The rover can construct from range imagery a geometric terrain representation; i.e., elevation map that includes uncertainty, unknown areas, and local features. An algorithm for constructing an elevation map from a single range image is presented: by virtue of working in spherical-polar space, the algorithm is independent of the desired map resolution and the orientation of the sensor, unlike algorithms that work in Cartesian space. Also presented is a two-stage matching technique (feature matching followed by iconic matching) that identifies the transformation T corresponding to the vehicle displacement between two viewing positions. To support legged locomotion over rough terrain, methods for evaluating regions of the constructed elevation maps as footholds are developed.

Hebert, M.

A perception system for a planetary explorer

To perform planetary exploration without human supervision, a complete autonomous robot must be able to model its environment and to locate itself while exploring its surroundings. For that purpose, the authors propose a modular perception system for an autonomous explorer. The perception system maintains a consistent internal representation of the observed terrain from multiple sensor views. The representation can be accessed from other modules through queries. The perception system is intended to be used by the Ambler, a six-legged vehicle being built at CMU. A partial implementation of the system using a range scanner is presented as well as experimental results on a testbed that includes the sensor, one computer-controlled leg, and obstacles on a sandy surface.

Hebert, M.