Back of the Envelope

Glenn Reynolds has pointed out a slashdot article about robots hunting down uncooperative human subjects. Unfortunately, whether for humor purposes or as a simple misunderstanding, they misread the original invitation for proposals, which actually says:

There are many research efforts within robotics in path planning, exploration, and mapping of indoor and outdoor environments. Operator control units are available that allow semi-autonomous map-based control of a team of robots. While the test environments are usually benign, they are slowly becoming longer and more complex. There has also been significant research in the game theory community involving pursuit/evasion scenarios. This topic seeks to merge these research areas and develop a software/hardware suit that would enable a multi-robot team, together with a human operator, to search for and detect a non-cooperative human subject. The main research task will involve determining the movements of the robot team through the environment to maximize the opportunity to find the subject, while minimizing the chances of missing the subject. If the operator is an active member of the search team, the software should minimize the chance that the operator may encounter the subject. As a simplification, the building layout could be given, although operating in an unknown environment with unknown obstacles is more realistic. The latter case should be studied at least in simulation. The software should maintain awareness of line-of-sight, as well as communication and sensor limits. It will be necessary to determine an appropriate sensor suite that can reliably detect human presence and is suitable for implementation on small robotic platforms. Additionally, the robot may not have the intelligence, sensing, or manipulative power to perform reconnaissance under full autonomy. For example, the robot may not be able to negotiate all obstacles, determine the course of action when confronted with difficult choices, or have sufficient team members to optimally search. Part of the research will involve determining what role the human operator will play in the search task. The system should flag the operator when assistance is required. Typical robots for this type of activity are expected to weigh less than 100 Kg and the team would have three to five robots.

Now, the problem is that the term used here is 'non-cooperative', not 'uncooperative,' and the two are not synonymous. Uncooperative, as a commonly used term, means someone who is "unwilling to work with you." It can be a euphemism for anyone you disagree with. Non-cooperative, in this context, is a technical term that has nothing to do with the subject's willingness or unwillingness. It refers to whether someone is actively helping in the task, namely, their own detection, and more specifically, actively helping in an agreed upon manner, such as by transmitting a radio signal. A non-cooperative subject could, in fact, be someone trying to hide from the robots, but it could equally well be someone who is unable to communicate, or who simply doesn't know how. If you have a system that detects cooperative subjects by radio transmitters, then someone standing on a hilltop waving a flag, but who lacks a radio transmitter, is non-cooperative.