Aidan Curtis
@AidanCurtis3
Followers
181
Following
244
Media
0
Statuses
17
Research Scientist @ Boston Dynamics Atlas Team | PhD from @MIT_CSAIL
Joined June 2013
RT @BostonDynamics: Atlas is demonstrating reinforcement learning policies developed using a motion capture suit. This demonstration was de….
0
5K
0
RT @MIT_CSAIL: Can we teach a robot its limits to do chores safely & correctly? 🧵. To help robots execute open-ended, multi-step tasks, MIT….
0
27
0
RT @nishanthkumar23: Can we get robots to improve at long-horizon tasks without supervision?. Our latest work tackles this problem by plann….
0
18
0
RT @nishanthkumar23: Ever heard about "Bilevel Planning" or "Task and Motion Planning", but been unsure what those words mean? Ever wanted….
0
18
0
RT @sugsharma: We had a paper in ICLR! The title is: "Map Induction: Compositional Spatial Submap Learning for Efficient Exploration in Nov….
0
30
0
RT @MIT_LISLab: If you're attending #ICRA2022, check out recent work led by @AidanCurtis3, @xiao_lin_fang and @CaelanGarrett on enabling ta….
0
4
0
RT @MIT_LISLab: Check out new work from @AidanCurtis3 on accelerating task and motion planning (TAMP) by learning generalized plans. This a….
0
1
0
RT @MIT_LISLab: Check out some of our recent work on intelligent open-world manipulation of unknown objects via task and motion planning!….
0
4
0
RT @tomssilver: PLOI: Planning with Learned Object Importance in Large Problem Instances using Graph Neural Networks.Paper: .
0
3
0
RT @MIT_LISLab: New blog alert! In our lab blog's first ever post, Leslie Kaelbling writes about the engineering science of embodied intell….
0
11
0
RT @MIT_LISLab: Classical AI planning algorithms are quite general-purpose, but are typically limited to finite action spaces and thus cann….
arxiv.org
Many planning applications involve complex relationships defined on high-dimensional, continuous variables. For example, robotic manipulation requires planning with kinematic, collision,...
0
4
0
Check out this exciting planning + RL + robotics project I've been working on. Thanks to everyone that helped out along the way!.
0
0
7
RT @dyamins: 1/7 A big problem with deepnet models of the brain is that they require training on huge supervised datasets. So even if they….
0
66
0