Abstract:
Conventional software debugging constructs are insu cient for debugging robotic software due primarily to the assumption of a deter- ministic, suspendable environment. What is needed is a method to extract and report infor- mation about robotic software execution while continuing execution in the real world environ- ment. A previously theorized debugging con- struct called a tracepoint has been implemented within both a C and a Python debugger. The NetBeans IDE was modi ed to provide an ex- tensible user interface. A plugin-based visu- alisation system for rendering trace data has also been implemented. Presently, plugins for the visualisation system have been created for rendering laser and ultrasonic range nder data from the Player robot library. Benchmark tests show that although there is still signi cant room for improvement, in one typical use case the system adds less than 1% overhead.