Obstacle Avoidance and Navigation in the Real World by a Seeing Robot Rover, Hans Moravec, 1980
<-- Previous  Next -->

Chapter 3: Overview

A typical run of the avoider system begins with a calibration of the cart's camera. The cart is parked in a standard position in front of a wall of spots. A calibration program (described in Chapter 4) notes the disparity in position of the spots in the image seen by the camera with their position predicted from an idealized model of the situation. It calculates a distortion correction polynomial which relates these positions, and which is used in subsequent ranging calculations.



Figure 3.1: The cart in its calibration pose

The cart is then manually driven to its obstacle course. Typically this is either in the large room in which it lives, or a stretch of the driveway which encircles the AI lab. Chairs, boxes, cardboard constructions and assorted debris serve as obstacles in the room. Outdoors the course contains curbing, trees, parked cars and signposts as well.



Figure 3.2: The cart indoors



Figure 3.3: The cart outdoors

The obstacle avoiding program is started. It begins by asking for the cart's destination, relative to its current position and heading. After being told, say, 50 meters forward and 20 to the right, it begins its maneuvers.

It activates a mechanism which moves the TV camera, and digitizes about nine pictures as the camera slides (in precise steps) from one side to the other along a 50 cm track.



Figure 3.4: A closeup of the slider mechanism

A subroutine called the interest operator (described in Chapter 5) is applied to the one of these pictures. It picks out 30 or so particularly distinctive regions (features) in this picture. Another routine called the correlator (Chapter 6) looks for these same regions in the other frames. A program called the camera solver (Chapter 7) determines the three dimensional position of the features with respect to the cart from their apparent movement image to image.

The navigator (Chapter 8) plans a path to the destination which avoids all the perceived features by a large safety margin. The program then sends steering and drive commands to the cart to move it about a meter along the planned path. The cart's response to such commands is not very precise.

After the step forward the camera is operated as before, and nine new images are acquired. The control program uses a version of the correlator to find as many of the features from the previous location as possible in the new pictures, and applies the camera solver. The program then deduces the cart's actual motion during the step from the apparent three dimensional shift of these features.

The motion of the cart as a whole is larger and less constrained than the precise slide of the camera. The images between steps forward can vary greatly, and the correlator is usually unable to find many of the features it wants. The interest operator/correlator/camera solver combination is used to find new features to replace lost ones.

The three dimensional location of any new features found is added to the program's model of the world. The navigator is invoked to generate a new path that avoids all known features, and the cart is commanded to take another step forward.

This continues until the cart arrives at its destination or until some disaster terminates the program.

Appendix 3 documents the evolution of the cart's internal world model in response to the scenery during a sample run.

An Objection

A method as simple as this is unlikely to handle every situation well. The most obvious problem is the apparently random choice of features tracked. If the interest operator happens to avoid choosing any points on a given obstruction, the program will never notice it, and might plan a path right through it.

The interest operator was designed to minimize this danger. It chooses a relatively uniform scattering of points over the image, locally picking those with most contrast. Effectively it samples the picture at low resolution, indicating the most promising regions in each sample area.

Objects lying in the path of the vehicle occupy ever larger areas of the camera image as the cart rolls forward. The interest operator is applied repeatedly, and the probability that it will choose a feature or two on the obstacle increases correspondingly. Typical obstructions are generally detected before its too late. Very small or very smooth objects are sometimes overlooked.

<-- Previous  Next -->