The Technology
Autonomous decision making under uncertainty is a fundamental problem in AI and robots, and is essential in numerous practical applications. Novel approaches are provided for decision making under uncertainty, for determining optimal actions online for single and multi agent systems considering partially observable domains where the state of the agent(s) and the environment is unknown. Depending on context, these approaches account for different soucres of uncertainty and ambiguity within the planning process, and are designed to be used in an online setting on potentially computationally limited agents. Based on these approaches, it is possible to develop solutions for numerous practical problems such as autonomous and safe navigation, robust autonomous operation in ambiguous settings, uncertainty reduction (e.g. 3D model improvement), active sensing and informative planning, and more.
Advantages
- Autonomous systems in an unknown environment with several look-alike features
- Real-time operation in high dimensional state spaces
- Study properties of geometrical objects invariant to certain deformations
- Principled way to account for uncertain data association as opposed to any domain-specific ad-hoc approach
- No additional computational costs
- Updating inference (belief) with incoming data
Applications and Opportunities
- Computationally efficient approaches for decision making under uncertainty are useful for a range of artificial intelligence applications, among others guidance of autonomous systems (navigations, autonomous car industry, autonomous robotics, quadrotors, defense industries, etc.)
- Ensure correct mapping and localization
Business Development Contacts