74.795-L02 Mobile Robotics Local Vision Assignment 3

Due: 28 November 2003


The following list contains additional information and comments about the project.


This page describes the third assignment for the course 74.795-L01 Mobile Robotics Using Local Vision.

The task of this assignment is the treasure hunt task of assignment 2. The difference is that in assignment 3, the main focus of the assignment is on generating an accurate map of the environment. After finding the ball, the robot should provide a map that would allow a treasure seeker to find and pick up the treasure.


The first problem in the assignment is to accurately measure and control the motion of the robot. For example, you may decide to implement a visual servoing loop to make sure that your robot moves a certain distance or turns a set number of degrees.

Another approach is to estimate the Ego-motion of the robot using feature (e.g., points, lines) in the environment.

There are several features that you can track in the environment.

You can track individual objects that you have recognized in the environment. For example, you can track the center of the ball or the left edge of an obstacle.

You can find line segments in the environment that you assume/know to be on the ground plane. In lectures, I presented a method to estimate the motion of the robots using these lines.

You can track individual points or spots (bright or dark spots) and estimate the motion from the flow field of these spots.

You can calculate the flow field over the entire image and approximate a motion from the observed motion of edges etc. However, this approach is computationally very expensive. An implementation of the Horn Schnuck algorithm is available in the Software section of the course page.


There are several different methods for representing a map in robotics. The most popular one are occupancy grids. To create an occupancy grid of the environment, you discretize the space into 10cm by 10cm squares and mark them as empty, occupied by an obstacle, or unknown.

In this assignment, you should estimate or measure the motion of the robots (possibly correlating the observed motion with a history of motor commands) to create an estimate of the position of the robot and the position of the obstacles in relation to the robot.

The Competition

The winner of this assignment will be determined in a treasure hunt competition which will take place on Friday, 28th of November 2003 at 17:00 in the basement of Machray Hall and the Linux lab.

The competition consists of five rounds. Each round the obstacles and treasures will be moved at random

A penalty of 30 secs. is assigned to a robot for every time the robot leaves the playing field, touches an obstacle or requires any other help form the human operator.

A robot receives one point everytime it finds a treasure and generates a map to find the treasure. In case, more than robot have the same number of points, the total sum of all the times for all runs in which the robot found the treasure are calculated. This determines the raw score.

Page was last updated on %s at %s.

", $mod_date, $mod_time); ?>
Hansjoerg Baltes (jacky)
Last modified: Thu Apr 25 15:55:12 NZST 2002