A biomimetic robotic system for localizing gunfire

Abstract

Using a biomimetic approach, a new method of acoustic signal processing was created which has tremendous advantages in complex acoustic environments. The biomimetic approach was used as the basis for a system to localize and identify sound sources in noisy and reverberant conditions. The algorithms are based on mammalian hearing and mimic the acoustic processing of the auditory periphery and midbrain. The system uses spectro-temporal cues exploited by the auditory system including such features as interaural time difference (ITD), interaural level difference (ILD), spectral profile, and periodicity content. The initial system of algorithms were designed and tested using the EARLAB [earlab.bu.edu] software modeling environment. The system of algorithms was then adapted to a mixed-signal real-time hardware solution and mounted on an iRobot PackBot robotic platform to perform simple behavioral tasks. The integrated system can detect and localize gunfire in a complex, reverberant acoustic environment and orient a camera towards the shooter. Accuracy in field tests with live fire was 1.5 deg in azimuth. The performance of the prototype platform demonstrates the potential of the biomimetic approach and its applications to practical problems for commercial, civilian, and military acoustic processing. [Work funded by ARL:DAAD19-00-2-0004.]