Modeling and Learning Constraints for Creative Tool Use

Improvisation is a hallmark of human creativity and serves a functional purpose in completing everyday tasks with novel resources. This is particularly exhibited in tool-using tasks: When the expected tool for a task is unavailable, humans often are able to replace the expected tool with an atypical one. As robots become more commonplace in human society, we will also expect them to become more skilled at using tools in order to accommodate unexpected variations of tool-using tasks. In order for robots to creatively adapt their use of tools to task variations in a manner similar to humans, they must identify tools that fulfill a set of task constraints that are essential to completing the task successfully yet are initially unknown to the robot. In this paper, we present a high-level process for tool improvisation (tool identification, evaluation, and adaptation), highlight the importance of tooltips in considering tool-task pairings, and describe a method of learning by correction in which the robot learns the constraints from feedback from a human teacher. We demonstrate the efficacy of the learning by correction method for both within-task and across-task transfer on a physical robot.

[1]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[2]  Charles C. Kemp,et al.  Challenges for robot manipulation in human environments [Grand Challenges of Robotics] , 2007, IEEE Robotics & Automation Magazine.

[3]  Derek C. Penn,et al.  Darwin's mistake: Explaining the discontinuity between human and nonhuman minds , 2008, Behavioral and Brain Sciences.

[4]  Alexander Schubert,et al.  The Role of Motion Dynamics in Abstract Painting , 2013, ICCC.

[5]  Patrick Beeson,et al.  TRAC-IK: An open-source library for improved solving of generic inverse kinematics , 2015, 2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids).

[6]  Allan Jabri,et al.  Universal Planning Networks , 2018, ICML.

[7]  Andrew G. Barto,et al.  Hierarchical Representations of Behavior for Efficient Creative Search , 2008, AAAI Spring Symposium: Creative Intelligent Systems.

[8]  S. Chernova,et al.  Feature Guided Search for Creative Problem Solving Through Tool Construction , 2020, Frontiers in Robotics and AI.

[9]  Darwin G. Caldwell,et al.  AffordanceNet: An End-to-End Deep Learning Approach for Object Affordance Detection , 2017, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[10]  Sergey Levine,et al.  One-shot learning of manipulation skills with online dynamics adaptation and neural network priors , 2015, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[11]  Heiko Hoffmann,et al.  Adaptive robotic tool use under variable grasps , 2014, Robotics Auton. Syst..

[12]  Bipin Indurkhya,et al.  Adapting Everyday Manipulation Skills to Varied Scenarios , 2018, 2019 International Conference on Robotics and Automation (ICRA).

[13]  Gil Weinberg,et al.  A generative physical model approach for enhancing the stroke palette for robotic drummers , 2016, Robotics Auton. Syst..

[14]  Dustin Stokes,et al.  Evolving Minimally Creative Robots , 2006 .

[15]  C. Kemp,et al.  Robot Manipulation of Human Tools : Autonomous Detection and Control of Task Relevant Features , 2006 .

[16]  Amitabha Mukerjee,et al.  Discovering implicit constraints in design , 2011, Artificial Intelligence for Engineering Design, Analysis and Manufacturing.

[17]  Ashok K. Goel,et al.  Human-Guided Object Mapping for Task Transfer , 2018, ACM Transactions on Human-Robot Interaction.

[18]  Y. Oshman,et al.  Averaging Quaternions , 2007 .

[19]  Andrea Lockerd Thomaz,et al.  Human-guided Trajectory Adaptation for Tool Transfer , 2019, AAMAS.

[20]  Andrea Lockerd Thomaz,et al.  Human-Robot Co-Creativity: Task Transfer on a Spectrum of Similarity , 2017, ICCC.

[21]  Marcin Andrychowicz,et al.  One-Shot Imitation Learning , 2017, NIPS.

[22]  S. Schaal Dynamic Movement Primitives -A Framework for Motor Control in Humans and Humanoid Robotics , 2006 .

[23]  Yiannis Aloimonos,et al.  Affordance detection of tool parts from geometric features , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[24]  C. Sammut,et al.  An Architecture for Tool Use and Learning in Robots , 2007 .

[25]  Yuchen Cui,et al.  Active Reward Learning from Critiques , 2018, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[26]  Zackory M. Erickson,et al.  Autonomous Tool Construction Using Part Shape and Attachment Prediction , 2019, Robotics: Science and Systems.

[27]  Eren Erdal Aksoy,et al.  Using structural bootstrapping for object substitution in robotic executions of human-like manipulation tasks , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[28]  Aude Billard,et al.  Iterative learning of grasp adaptation through human corrections , 2012, Robotics Auton. Syst..

[29]  Carme Torras,et al.  A robot learning from demonstration framework to perform force-based manipulation tasks , 2013, Intelligent Service Robotics.

[30]  Mike Stilman,et al.  Using environment objects as tools: Unconventional door opening , 2014, 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[31]  Todd Lubart,et al.  Educational Robotics and Robot Creativity: An Interdisciplinary Dialogue , 2021, Frontiers in Robotics and AI.

[32]  Oliver Kroemer,et al.  A kernel-based approach to direct action perception , 2012, 2012 IEEE International Conference on Robotics and Automation.

[33]  Finale Doshi-Velez,et al.  Robust and Efficient Transfer Learning with Hidden Parameter Markov Decision Processes , 2017, AAAI.

[34]  J. Sinapov,et al.  Detecting the functional similarities between tools using a hierarchical representation of outcomes , 2008, 2008 7th IEEE International Conference on Development and Learning.

[35]  Andrea Lockerd Thomaz,et al.  Robot Learning from Human Teachers , 2014, Robot Learning from Human Teachers.

[36]  Pat Langley,et al.  Creating and Using Tools in a Hybrid Cognitive Architecture , 2018, AAAI Spring Symposia.

[37]  Sarathy,et al.  MacGyver Problems: AI Challenges for Testing Resourcefulness and Creativity , 2018 .

[38]  Ashok K. Goel,et al.  Analogy and metareasoning: Cognitive strategies for robot learning , 2020 .

[39]  Brett Browning,et al.  A survey of robot learning from demonstration , 2009, Robotics Auton. Syst..

[40]  Ashok K. Goel Design, Analogy, and Creativity , 1997, IEEE Expert.

[41]  Pieter E. Vermaas,et al.  Technical Functions: On the Use and Design of Artefacts , 2010 .

[42]  K. Vaesen The cognitive bases of human tool use , 2012, Behavioral and Brain Sciences.

[43]  Anca D. Dragan,et al.  Learning from Physical Human Corrections, One Feature at a Time , 2018, 2018 13th ACM/IEEE International Conference on Human-Robot Interaction (HRI).

[44]  Nikolaus Correll,et al.  Reducing the Barrier to Entry of Complex Robotic Software: a MoveIt! Case Study , 2014, ArXiv.

[45]  Silvio Savarese,et al.  Learning task-oriented grasping for tool manipulation from simulated self-supervision , 2018, Robotics: Science and Systems.

[46]  Maya Cakmak,et al.  Keyframe-based Learning from Demonstration , 2012, Int. J. Soc. Robotics.

[47]  Stefan Schaal,et al.  Learning and generalization of motor skills by learning from demonstration , 2009, 2009 IEEE International Conference on Robotics and Automation.

[48]  Yuchen Cui,et al.  Understanding the Relationship between Interactions and Outcomes in Human-in-the-Loop Machine Learning , 2021, IJCAI.

[49]  Eric L. Sauser,et al.  Tactile guidance for policy refinement and reuse , 2010, 2010 IEEE 9th International Conference on Development and Learning.

[50]  Peter Stone,et al.  Transfer Learning for Reinforcement Learning Domains: A Survey , 2009, J. Mach. Learn. Res..