# From Real World to Logic and Back: Learning Generalizable Relational Concepts For Long Horizon Robot Planning Source: [From Real World to Logic and Back: Learning Generalizable Relational Concepts For Long Horizon Robot Planning]() Collection index: [llms.txt]() Data updated: 2025-10-26T05:50:18.755Z Authors: Naman Shah, Jayesh Nagpal, Siddharth Srivastava Published: 2024-02-19T06:28:21.000Z ## Abstract Robots still lag behind humans in their ability to generalize from limited experience, particularly when transferring learned behaviors to long-horizon tasks in unseen environments. We present the first method that enables robots to autonomously invent symbolic, relational concepts directly from a small number of raw, unsegmented, and unannotated demonstrations. From these, the robot learns logic-based world models that support zero-shot generalization to tasks of far greater complexity than those in training. Our framework achieves performance on par with hand-engineered symbolic models, while scaling to execution horizons far beyond training and handling up to 18$\\times$ more objects than seen during learning. The results demonstrate a framework for autonomously acquiring transferable symbolic abstractions from raw robot experience, contributing toward the development of interpretable, scalable, and generalizable robot planning systems. Project website and code: https://aair-lab.github.io/r2l-lamp. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Predicate and Skill Learning on General Robotic Manipulation Tasks](): Predicate and Skill Learning; General Robotic Manipulation Tasks; Number of Demonstrations: 200. ## Original sources and implementation [Original paper]() [PDF]()