Efficiently testing for unboundedness and m-handed assembly

We address the problem of efficiently determining if the intersection of a given set of d-dimensional halfspaces is unbounded. It is shown that detecting unboundedness can be reduced to a single linear range computation followed by a single linear feasibility test. In contrast, detecting unboundedness is at least as hard as linear feasibility testing and maximization. Our analysis suggests that algorithms for establishing linear unboundedness can be used as a basis of simple and practical algorithms in motion planning, insertability analysis and assembly planning. We show that m-handed assembly planning can be reduced to testing for unboundedness. A valid motion sequence can be computed in polynomial time, if the parts are not already separated in their initial placement. No polynomial algorithms were previously known for this problem. We present experimental results obtained with an implementation of our algorithms.