{"id":577041,"date":"2019-04-08T08:59:33","date_gmt":"2019-04-08T15:59:33","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?p=577041"},"modified":"2019-04-08T09:49:21","modified_gmt":"2019-04-08T16:49:21","slug":"rapidly-enabling-autonomy-at-scale-with-simulation","status":"publish","type":"post","link":"https:\/\/www.microsoft.com\/en-us\/research\/blog\/rapidly-enabling-autonomy-at-scale-with-simulation\/","title":{"rendered":"Rapidly enabling autonomy at scale with simulation"},"content":{"rendered":"
<\/a>Autonomous Systems have attracted a lot of attention as they promise to improve efficiency, reduce cost and most importantly take on tasks that are too dangerous for humans. However, building a real-world autonomous system that would operate safely at scale is a very difficult task. For example, the first self-sufficient autonomous cars were demonstrated by Carnegie Mellon University\u2019s Navigation Laboratory in the 1980s and while there has been great progress, achieving safe and reliable autonomy continues to intrigue the brightest of minds.<\/p>\n We are excited to announce that Microsoft Research is teaming up with Carnegie Mellon University to explore and test these ideas and tool chains. Specifically, Microsoft will be partnering with the Carnegie Mellon team led by Sebastian Scherer and Matt Travers to solve the DARPA Subterranean Challenge<\/a>. The challenge requires building robots that can autonomously search tunnels, caves and underground structures. This exacting task requires a host of technologies that include mapping, localization, navigation, detection, planning, and so on, and consequently the collaboration will center on toolchains that would enable rapid development for autonomous systems by utilizing simulations, exploiting modular structure and providing robustness via statistical machine learning techniques.<\/p>\n We aim to explore how to enable developers, engineers and researchers to build autonomy across a wide variety of domains without needing to spend additional decades of research and development.\u00a0We need tools that allow subject matter expertise, specific to the application domain, to be fused with the knowledge we\u2019ve garnered developing various machine learning, AI and robotic systems over the last few decades.<\/p>\n Field robotics is hard, due to the effort, expense, and time required in designing, building, deploying, testing, and validating physical systems. Moreover, the recent gamut of Deep Learning and Reinforcement Learning methodologies requires data at a scale that is impossible to collect in the real-world. The ability to run high-fidelity simulations at scale on Azure, is an integral part of this process that allows rapid prototyping, engineering and efficient testing. AI centric simulations, such as AirSim<\/a> allow generation of meaningful training data that greatly helps in tackling the challenge of the high sample-complexity of popular machine learning and reinforcement learning methods.<\/p>\n Autonomous systems need to make a sequence of decisions under a host of uncertain factors that include the environment, other actors, its own perception and dynamic system. Consequently, techniques such as imitation and reinforcement learning lie at the foundation of building autonomous systems. For example, in a collaboration with Technion, Israel<\/a>, hi-fidelity simulations in AirSim were used to train for an autonomous Formula SAE design competition car via imitation learning (see Figure 1.) While great success has been attained in the solving of arcade games, achieving real-world autonomy is non-trivial. Besides the obvious challenge of requiring a large amount of training data, further enhancements are needed to make ML paradigms such as reinforcement learning and imitation learning accessible to the non-ML crowd.<\/p>\n\t