mlsanityData to 7 Oct 2026

Inductive Learning of Robot Task Knowledge from Raw Data and Online Expert Feedback

arXiv 2501.07507 ↗First posted 13 Jan 2025cs.AI cs.LO cs.ROcited by 2

Not on the map. Why?

Abstract (arXiv)

The increasing level of autonomy of robots poses challenges of trust and social acceptance, especially in human-robot interaction scenarios. This requires an interpretable implementation of robotic cognitive capabilities, possibly based on formal methods as logics for the definition of task specifications. However, prior knowledge is often unavailable in complex realistic scenarios. In this paper, we propose an offline algorithm based on inductive logic programming from noisy examples to extract task specifications (i.e., action preconditions, constraints and effects) directly from raw data of few heterogeneous (i.e., not repetitive) robotic executions. Our algorithm leverages on the output of any unsupervised action identification algorithm from video-kinematic recordings. Combining it with the definition of very basic, almost task-agnostic, commonsense concepts about the environment, which contribute to the interpretability of our methodology, we are able to learn logical axioms encoding preconditions of actions, as well as their effects in the event calculus paradigm. Since the quality of learned specifications depends mainly on the accuracy of the action identification algorithm, we also propose an online framework for incremental refinement of task knowledge from user feedback, guaranteeing safe execution. Results in a standard manipulation task and benchmark for user training in the safety-critical surgical robotic scenario, show the robustness, data- and time-efficiency of our methodology, with promising results towards the scalability in more complex domains.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 37 of its 93 references that are in the map. First posted on arXiv 13 Jan 2025.

Builds on

37 of 93 references.

References · 37

  1. 2019RLBench: The Robot Learning Benchmark & Learning Environmentcited by 669
  2. 2022LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Actioncited by 435
  3. 2017Learning Explanatory Rules from Noisy Datacited by 210
  4. 2017Vision-Based Multi-Task Manipulation for Inexpensive Robots Using End-To-End Learning from Demonstrationcited by 100
  5. 2019ASP-Core-2 Input Language Formatcited by 77
  6. 2020Learning programs by learning from failurescited by 73
  7. 2021From Statistical Relational to Neurosymbolic Artificial Intelligence: a Surveycited by 72
  8. 2023Data-Efficient Learning of Natural Language to Linear Temporal Logic Translators for Robot Task Specificationcited by 38
  9. 2014Efficient Model Learning for Human-Robot Collaborative Taskscited by 35
  10. 2019Explainability in Human-Agent Systemscited by 34
  11. 2018Trust-Aware Decision Making for Human-Robot Collaboration: Model Learning and Planningcited by 32
  12. 2021Differentiable Inductive Logic Programming for Structured Examplescited by 26
25 more
  1. 2021Techniques for Symbol Grounding with SATNetcited by 24
  2. 2023Enumerating Safe Regions in Deep Neural Networks with Provable Probabilistic Guaranteescited by 19
  3. 2017Learning End-to-end Multimodal Sensor Policies for Autonomous Navigationcited by 16
  4. 2023TGRL: An Algorithm for Teacher Guided Reinforcement Learningcited by 16
  5. 2023Deep Explainable Relational Reinforcement Learning: A Neuro-Symbolic Approachcited by 15
  6. 2022Learning Reward Functions for Robotic Manipulation by Observing Humanscited by 14
  7. 2022Behavior Trees in Robot Control Systemscited by 13
  8. 2017Best-Effort Inductive Logic Programming via Fine-grained Cost-based Hypothesis Generationcited by 11
  9. 2023Human-in-the-loop Embodied Intelligence with Interactive Simulation Environment for Surgical Robot Learningcited by 11
  10. 2020Autonomous task planning and situation awareness in robotic surgerycited by 10
  11. 2023Constrained Reinforcement Learning and Formal Verification for Safe Colonoscopy Navigationcited by 9
  12. 2020Conflict-driven Inductive Logic Programmingcited by 8
  13. 2023Logic programming for deliberative robotic task planningcited by 8
  14. 2023Learning Logic Specifications for Soft Policy Guidance in POMCPcited by 7
  15. 2024Learning Logic Specifications for Policy Guidance in POMDPs: an Inductive Logic Programming Approachcited by 7
  16. 2016Real-time analysis of cataract surgery videos using statistical modelscited by 6
  17. 2019Weakly Supervised Recognition of Surgical Gesturescited by 6
  18. 2021Autonomous tissue retraction with a biomechanically informed logic based frameworkcited by 6
  19. 2019Overcoming Some Drawbacks of Dynamic Movement Primitivescited by 5
  20. 2020Dynamic Movement Primitives: Volumetric Obstacle Avoidance Using Dynamic Potential Functionscited by 5
  21. 2021Online Learning Probabilistic Event Calculus Theories in Answer Set Programmingcited by 4
  22. 2022Deliberation in autonomous robotic surgery: a framework for handling anatomical uncertaintycited by 4
  23. 2020Axiom Learning and Belief Tracing for Transparent Decision Making in Roboticscited by 3
  24. 2021Unsupervised identification of surgical robotic actions from small non homogeneous datasetscited by 3
  25. 2020Improving rigid 3D calibration for robotic surgerycited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Modeling Arbitrarily Applicable Relational Responding with the Non-Axiomatic Reasoning System: A Machine Psychology Approachcited by 0
  2. 2026Explaining Reinforcement Learning Agents via Inductive Logic Programmingcited by 0