Recently, robots and automation systems have been at the front of research with the majority of systems still operating independently using onboard computation, memory manipulation and communication. With improvements in communication technology and the increasing availability of network, new approaches where robot and automation processing is performed remotely with access to large scale datasets, support a range of functions. Cloud Robotics supplements performance enhancement of robotics and autonomous systems by providing a global infrastructure in innovative ways. This paper summarizes recent research into five traits of Cloud Robotics for performance enhancement in robotics and autonomous systems: 1) Remote Brain, 2) Big Data and Shared Knowledge-base, 3) Collective Learning, 4) Intelligence and Behavior, and 5) Cloud architectures. Towards the end, in this survey, we present future directions for research in cloud robotics.