Assignment 2 description

In Assignment 2, all problems are set in a Maze of the same type as Assignment 1.

However, now there are a large set of cars/drones in the same environment, with different goal locations.

The unity project, that can be found here: Gits

You will solve four problems (P1-P4). Each problem is setup in a different "Scene" of the project.

P1 Traffic Car
P2 Traffic Drone
P3 Formation Car
P4 Formation Drone

The vehicles: Cars and Drones

The vehicles are basically the same as in Assignment 1, but to keep the focus on coordination, we limit the top speed of the car (making it less important to device super smooth trajectories), and we make the drones crash resistant (no reduced accelerations after crashing). Furthermore, to make the drones visible from afar, we swap change their skins into capsules, see figure below. The yellow areas are goal positions and the gray areas are start positions.

Screen Shot 2024-02-15 at 12.40.52.png

Problems P1 and P2: Traffic

In the traffic problems there is a set of agents (cars/drones), each having a separate goal position. The problem is to minimize the time until all agents have passed their respective goal positions (goals turn blue when completed).

The motivation for P1 and P2 is given by it's similarity to a wide range of scenarios involving robots or autonomous vehicle that share workspace with each other, and sometimes also humans. Reaching a goal without collisions with other agents is very important.

Depending on the maps, the traffic problem can bring quite different challenges. We will now present a set of maps that your agent can encounter. All of these can be found in the Resources/Text folder, and loaded using the MapManager object, just as in Assignment 1.

terrain_open (possible collisions from all angles, no static obstacles)
terrain_semi_open (possible collisions from all angles, including static obstacles)
terrain_intersection (all agents converge to a four way intersection, possible collisions from 90, 180, 270 degrees directions)
terrain_highway (all agents must squeeze through a bottle neck, forcing alignment with vehicles moving in roughly the same direction)
terrain_onramp (similar to highway, but with some agents coming in at 45 degree angle, like a highway onramp)

The illustrations below show the different terrains.

terrain_open

Screen Shot 2024-02-15 at 09.04.31.png

All agents are positioned in a ring, with their goal on the opposite side. Note that there is a "cheating" solution to this configuration that involves running all agents after each other in a circle. This is not allowed!

terrain_semi_open

Screen Shot 2024-02-15 at 09.16.02.png

terrain_intersection

Screen Shot 2024-02-15 at 15.47.51.png

terrain_highway

Screen Shot 2024-02-15 at 09.18.52.png

terrain_onramp

Screen Shot 2024-02-15 at 09.24.03.png

As noted above, the time stops when the last agent has reached its goal marker.

Problems P3 and P4: Formation

Even though the terrains intersection and highway have some element of formation keeping, P3 and P4 test a different kind of formation keeping.

As illustrated below, the terrains now have 5 agents, and clusters of 5 gates spread over the area. Each cluster measures the time from when the first gate is passed, until the last is passed (ideally this is zero, if all 5 agents pass though the 5 gates at the same time). At the same time, another clock keeps track of the time from start until all clusters are passed. Then these times are added. The gates have traffic lights, showing red before the clocks are started, yellow when the clocks are running, and green when they are stopped/completed.

A good solution is thus that the 5 agents move in a synchronized formation, such that each gate-cluster is passed at the same time, while rapidly moving between the clusters to complete the overall course as fast as possible.

Screen Shot 2024-02-15 at 09.03.09.png

Progress report

The same routine as last assignment. Use this Google Sheet Links to an external site..