6 papers · 1 filter
Follow the Signs: Using Textual Cues and LLMs to Guide Efficient Robot Navigation
Jing Cao, Nishanth Kumar, Aidan Curtis
Autonomous navigation in unfamiliar environments often relies on geometric mapping and planning strategies that overlook rich semantic cues such as signs, room numbers, and textual…
ARCH: Hierarchical Hybrid Learning for Long-Horizon Contact-Rich Robotic Assembly
Jiankai Sun, Aidan Curtis, Yang You +8
Generalizable long-horizon robotic assembly requires reasoning at multiple levels of abstraction. While end-to-end imitation learning (IL) is a promising approach, it typically req…
Flow-based Domain Randomization for Learning and Sequencing Robotic Skills
Aidan Curtis, Eric Li, Michael Noseworthy +5
Domain randomization in reinforcement learning is an established technique for increasing the robustness of control policies trained in simulation. By randomizing environment prope…
Towards Practical Finite Sample Bounds for Motion Planning in TAMP
Seiji Shaw, Aidan Curtis, Leslie Pack Kaelbling +2
When using sampling-based motion planners, such as PRMs, in configuration spaces, it is difficult to determine how many samples are required for the PRM to find a solution consiste…
Partially Observable Task and Motion Planning with Uncertainty and Risk Awareness
Aidan Curtis, George Matheos, Nishad Gothoskar +4
Integrated task and motion planning (TAMP) has proven to be a valuable approach to generalizable long-horizon robotic manipulation and navigation problems. However, the typical TAM…
Trust the PRoC3S: Solving Long-Horizon Robotics Problems with LLMs and Constraint Satisfaction
Aidan Curtis, Nishanth Kumar, Jing Cao +2
Recent developments in pretrained large language models (LLMs) applied to robotics have demonstrated their capacity for sequencing a set of discrete skills to achieve open-ended go…