The 2004 Mobile Robot Competition and Exhibition

Running services in many small processes improves fault tolerance since any number of services can fail due to programming faults without affecting the rest of the system. While it is clearly important to be able to handle a wide range of failures, application authors should not be required to implement routines to test and react in every known mode of failure for every application, even if the failures are abstracted to a common interface. Thus, the framework also provides transparent fault-tolerance to users of system services. Errors in software and hardware are detected, and corrective action is taken. Services can be restarted or removed from the system, and clients are reconnected to the same service or to another service implementing the same interface without intervention from the application programmer. The Washington University team successfully demonstrated its failure-tolerant framework on its robot, Lewis (figure 6).