Pantelis, Peter, Steven A. Cholewiak, Tim Gerstner, Gaurav Kharkwal, Kevin Sanik, Ari Weinstein, Chia-Chien Wu, and Jacob Feldman. “Perceiving intelligent action: Experiments in the interpretation of intentional motion.”
URL1 URL2
People routinely make inferences about the mental states of others so that they can make predictions about what other agents are likely to do in the future. The motion of objects in the world is an especially salient cue for making these inferences. Even the motion of simple geometric shapes can convey the impression that these shapes of underlying intentions, goals, and mental states (Heider & Simmel, 1944). The aim of this project is to develop a theoretical model of the perception of intentions, shedding light onto both the function of the human (biological) perceptual system, and the design of computational models that drive artificial systems (robots). To this end, an interdisciplinary group of IGERT students created a novel virtual environment populated by intelligent autonomous agents (we call them IMPs), and endowed these agents with human-like capacities: goals, real-time perception, memory, planning, and decision making. This work has been inspired by research in artificial life (e.g. Terzopoulos et al, 1994; Yaeger, 1994).