Register now After registration you will be able to apply for this opportunity online.
This opportunity is not published. No applications will be accepted.
Learning to Plan
Learning to Plan
Recent techniques based on machine learning enabled robotics system to perform many difficult tasks, such as manipulation or navigation.
While networks are provably good in performing reactive tasks, as obstacle avoidance, they generally fail to make long-term plans to solve complicated tasks (e.g. navigate through a maze). In this project, we will develop techniques to let a robot reason in time and plan to perform actions to achieve high level goals.
Recent techniques based on machine learning enabled robotics system to perform many difficult tasks, such as manipulation or navigation. While networks are provably good in performing reactive tasks, as obstacle avoidance, they generally fail to make long-term plans to solve complicated tasks (e.g. navigate through a maze). In this project, we will develop techniques to let a robot reason in time and plan to perform actions to achieve high level goals.
The project aims to develop techniques based on machine learning to let a robot plan actions to achieve high-level goals.
The project aims to develop techniques based on machine learning to let a robot plan actions to achieve high-level goals.