Wireless video sensor networks for sparse, resource-constrained, multi-robot teams

Small-size robots provide access and maneuverability in the tight confines of highly rubbled and uncertain environments such as those encountered in Urban Search and Rescue (USAR). Small size also provides easy portability and deployability and the potential for redundancy through multi-robot teaming. Unfortunately, small size does not diminish the data demands of these applications, such as high-resolution imagery and other forms of high bandwidth data. Furthermore, achieving redundancy in tight environments requires wireless operation to avoid the entanglement of tethers, but wireless communication links have proven unreliable in such environments. The net effect of this is a set of robust networking requirements that include high bandwidth, low latency, and low power with multi-hop routing in a sparse and highly volatile network configuration, which has been collectively difficult to achieve. Our metric for benchmarking these requirements is a stream of uncompressed 320 x 240, 24-bit color images updated at 1 frame per second (roughly 1.8 Mbps - image compression is not the focus of this research as it only serves to increase the possible resolution or frame rate). No existing ad hoc wireless sensor network approaches have been able to achieve these requirements. Wi-Fi requires high power and size and does not have the latency, while Zig-bee does not have the bandwidth. Instead, this work focuses on augmenting the Bluetooth protocol, which is master/slave based, with a hybrid, multi-hop routing protocol. Bluetooth has the desired low power and high bandwidth characteristics, but lacks multi-hop routing and rapid recovery. In this paper, a hybrid routing protocol for ad hoc multi-robot networking is described that features: (1) high-bandwidth, (2) low power, and (3) low latency of data traffic for sparse, highly volatile networks-exactly what is required for large teams of highly distributed, small-scale robots. Furthermore, this paper compares simulations and robot implementations of different routing protocols over Bluetooth sensor networks and demonstrates the viability of our protocol as a wireless network solution for multi-robot teams characterized by high mobility in difficult RF environments. To the best of our knowledge, the work presented in this paper is the first attempt at comparison of different routing protocols for real robots with physical experiments over Bluetooth sensor networks.