Transferable Task Execution from Pixels through Deep Planning Domain Learning

2020-03-08 · Kei Kase, Chris Paxton, Hammad Mazhar, Tetsuya OGATA, Dieter Fox

While robots can learn models to solve many manipulation tasks from raw visual input, they cannot usually use these models to solve new problems. On the other hand, symbolic planning methods such as STRIPS have long been able to solve new problems given only a domain definition and a symbolic goal, but these approaches often struggle on the real world robotic tasks due to the challenges of grounding these symbols from sensor data in a partially-observable world. We propose Deep Planning Domain Learning (DPDL), an approach that combines the strengths of both methods to learn a hierarchical model. DPDL learns a high-level model which predicts values for a large set of logical predicates consisting of the current symbolic world state, and separately learns a low-level policy which translates symbolic operators into executable actions on the robot. This allows us to perform complex, multi-step tasks even when the robot has not been explicitly trained on them. We show our method on manipulation tasks in a photorealistic kitchen scenario.

📄 PDF Abstract BibTeX arXiv:2003.03726

Code (0)

등록된 구현이 없습니다.

Planning with Abstract Learned Models While Learning Transferable Subtasks

2019-12-16 · John Winder, Stephanie Milani, Matthew Landen, Erebus Oh 외

We introduce an algorithm for model-based hierarchical reinforcement learning to acquire self-contained transition and reward models suitable for probabilistic planning at multiple levels of abstraction. We call this fra…

Hierarchical Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Learning Transferable Motor Skills for Geometry-Aware Robotic Surface Tasks

2026-05-24 · Miroslav David, Karla Stepanova, Robert Babuska arxiv

Robotic surface-interaction tasks, such as spray painting or welding, require both accurate geometric planning and precise motion execution. While modern motion planners generate valid geometric paths, they often lack th…

Motion Planning

Pixels to Proofs: Probabilistically-Safe Latent World Model Control via Parallel Conformal Robust MPC

2026-06-14 · Devesh Nath, Anutam Srinivasan, Haoran Yin, Ruitong Jiang 외 arxiv

We present SLS^2, a framework for safe feedback motion planning from pixels using robust model predictive control (MPC) in learned latent world models. Our approach trains an action-conditioned joint-embedding world mode…

Motion Planning

Multimodal Contextualized Plan Prediction for Embodied Task Completion

2023-05-10 · Mert İnan, Aishwarya Padmakumar, Spandana Gella, Patrick Lange 외

Task planning is an important component of traditional robotics systems enabling robots to compose fine grained skills to perform more complex tasks. Recent work building systems for translating natural language to execu…

Prediction Task Planning

Fast PET Scan Tumor Segmentation using Superpixels, Principal Component Analysis and K-means Clustering

2017-10-18 · Yeman B. Hagos, Vu H. Minh, Saed Khawaldeh, Usama Pervaiz 외

Positron Emission Tomography scan images are extensively used in radiotherapy planning, clinical diagnosis, assessment of growth and treatment of a tumor. These all rely on fidelity and speed of detection and delineation…

Clustering Superpixels Tumor Segmentation