Goal-Oriented Long-Lived Systems
The Goal-Oriented Long-Lived Systems (GOALS) Lab performs research around the problems of behaviour generation for autonomous systems. In particular we focus on long-term autonomy and task and mission planning for mobile robots which must operate for extended periods (days, weeks or months) in dynamic, uncertain environments. To create long-term autonomous behaviour we explore the application of artificial intelligence techniques to robots, particularly planning under uncertainty and machine learning, such that the longer robots act in an environment, the better they perform.
RT @MauriceFallon: Reminder: funded position - deadline approaching. Join my group working on mobile robot navigation. I particularly welc…
RT @mmattamala: Really nice work on reactive control by @GOALS_oxford colleagues @lbrudermueller and @hawesie !
RT @hawesie: I’m very pleased to see some @oxfordrobots (@dynamicrobots @GOALS_oxford) work in here. Spot is an awesome platform for robust…
RT @UniofOxford: PHOTOS: @oxfordrobots at Blenheim Palace 🤖 The Boston Dynamics Spot is being used at the palace to gather data about spec…
If you're at #NeurIPS2022 and interested in offline RL, please make sure you check out Marc's poster. It's his first in-person presentation on his PhD. Given he's literally about to submit his thesis, please go and help him make up for missed experiences! https://t.co/upI5SzGaSe
RT @lbrudermueller: You want your robot to be reactive, but CMA-ES is too slow for optimizing joint-space trajectories in an MPC loop? Exci…
RT @MarcRigter: The camera-ready version of our #NeurIPS2022 paper, Robust Adversarial Model-Based Offline (RAMBO) Reinforcement Learning,…
A big week in GOALS. Huge congrats to @m_budd for getting his paper accepted at #CoRL22 and @MarcRigter for his accept at #NeurIPS2022. Both papers were really improved by interaction with the reviewers during the rebuttal phase.
RT @hawesie: Come join both the @GOALS_oxford and @UKAEAofficial teams at the same time as a postdoc. https://t.co/6Yg5QqtGro