ABSTRACT
Our analysis of human sampling decision data reveals that scientists adapt their sampling strategies to balance multiple objectives based on two key factors: the current level of information about the environment, and the availability of sampling location options with large potential rewards. While this work is only a beginning step towards the development of cognitive-compatible robotic decision algorithms, our findings show by better understanding human decision processes, robots can use extremely simple algorithms to connect experts' high-level objectives to desired sampling locations while balancing multiple objectives. Going forward, exploring how humans coordinate and prioritize multiple objectives under more sophisticated scientific exploration scenarios, such as with multiple competing hypotheses, with hypotheses regarding multiple variables, or with additional sampling objectives, would be helpful to explore. These understandings could help our robots produce explainable sampling strategies that are well-aligned with humans' high level goals, and improve humans' trust and confidence during teaming. These cognitive understandings could also allow robots to identify potential vulnerabilities in human decisions, such as biases and fatigue, and provide targeted support to enhance scientific outcomes. In addition, we expect that these cognitive insights could complement existing robotic decision methods by informing which algorithms to use, and eventually empower robots to become intelligent teammates that can truly participate in the decision-making process.
- Jamshid Aghaei, Nima Amjady, and Heidar Ali Shayanfar. 2011. Multi-objective electricity market clearing considering dynamic security by lexicographic optimization and augmented epsilon constraint method. Applied Soft Computing 11, 4 (2011), 3846--3858.Google ScholarDigital Library
- Fatima M Albar and Antonie J Jetter. 2009. Heuristics in decision making. In PICMET'09--2009 Portland International Conference On Management Of Engineering & Technology. IEEE, 578--584.Google ScholarCross Ref
- Robert C Anderson, Dan Adamo, Debra Buczkowski, James Dohm, Tamas Haidegger, Tom Jones, Gregg Podnar, and Danielle Wyrick. 2021. Next frontier in planetary geological reconnaissance: Low-latency telepresence. Icarus 368 (2021), 114558.Google ScholarCross Ref
- Connor Brooks and Daniel Szafir. 2019. Balanced Information Gathering and Goal-Oriented Actions in Shared Autonomy. In 2019 14th ACM/IEEE International Conference on Human-Robot Interaction (HRI). IEEE, 85--94.Google Scholar
- Connor Brooks and Daniel Szafir. 2019. Balanced Information Gathering and Goal-Oriented Actions in Shared Autonomy. In 2019 14th ACM/IEEE International Conference on Human-Robot Interaction (HRI). 85--94. https://doi.org/10.1109/ HRI.2019.8673192Google Scholar
- Erdem Biyik, Dylan P. Losey, Malayandi Palan, Nicholas C. Landolfi, Gleb Shevchuk, and Dorsa Sadigh. 0. Learning reward functions from diverse sources of human feedback: Optimally integrating demonstrations and preferences. The International Journal of Robotics Research 0, 0 (0), 02783649211041652. https://doi.org/10.1177/02783649211041652 arXiv:https://doi.org/10.1177/02783649211041652Google ScholarDigital Library
- Christy M Caudill, Alexandra J Pontefract, Gordon R Osinski, Livio L Tornabene, Eric A Pilles, Melissa Battler, Raymond Francis, Etienne Godin, Anna Grau Galofre, Timothy Haltigin, et al. 2019. CanMars mission Science Team operational results: Implications for Operations and the Sample Selection Process for Mars Sample Return (MSR). Planetary and Space Science 172 (2019), 43--56.Google ScholarCross Ref
- Jessie YC Chen, Stephanie Quinn, Julia Wright, Michael Barnes, Daniel Barber, and David Adams. 2013. Human-Agent Teaming for Robot Management in Multitasking Environments. In 2013 8th ACM/IEEE International Conference on Human-Robot Interaction (HRI). IEEE, 103--104.Google Scholar
- Weizhe Chen, Roni Khardon, and Lantao Liu. 0. Adaptive Robotic Information Gathering via non-stationary Gaussian processes. The International Journal of Robotics Research 0, 0 (0), 02783649231184498. https://doi.org/10.1177/ 02783649231184498 arXiv:https://doi.org/10.1177/02783649231184498Google ScholarDigital Library
- I. Das and J. E. Dennis. 1997. A closer look at drawbacks of minimizing weighted sums of objectives for Pareto set generation in multicriteria optimization problems. Structural optimization 14, 1 (01 Aug 1997), 63--69. https: //doi.org/10.1007/BF01197559Google ScholarCross Ref
- Cary Deck and Salar Jahedi. 2015. The effect of cognitive load on economic decision making: A survey and new experiments. European Economic Review 78 (2015), 97--119. https://doi.org/10.1016/j.euroecorev.2015.05.004Google ScholarCross Ref
- Julie Drevet, Jan Drugowitsch, and Valentin Wyart. 2022. Efficient stabilization of imprecise statistical inference through conditional belief updating. Nature Human Behaviour 6, 12 (2022), 1691--1704.Google ScholarCross Ref
- Terrence Fong, Andrew Abercromby, Maria G Bualat, Matthew C Deans, Kip V Hodges, Jose M Hurtado Jr, Rob Landis, Pascal Lee, and Debra Schreckenghost. 2010. Assessment of Robotic Recon for Human Exploration of the Moon. Acta Astronautica 67, 9--10 (2010), 1176--1188.Google ScholarCross Ref
- Gerd Gigerenzer and Wolfgang Gaissmaier. 2011. Heuristic decision making. Annual review of psychology 62 (2011), 451--482.Google Scholar
- Eric Hsiung, Eric Rosen, Vivienne Bihe Chi, and Bertram F Malle. 2022. Learning Reward Functions from a Combination of Demonstration and Evaluative Feedback. In 2022 17th ACM/IEEE International Conference on Human-Robot Interaction (HRI). IEEE, 807--811.Google ScholarDigital Library
- Ching-Lai Hwang, Young-Jou Lai, and Ting-Yun Liu. 1993. A new approach for multiple objective decision making. Computers Operations Research 20, 8 (1993), 889--899. https://doi.org/10.1016/0305-0548(93)90109-VGoogle ScholarDigital Library
- Maani Ghaffari Jadidi, Jaime Valls Miro, and Gamini Dissanayake. 2019. Samplingbased incremental information gathering with applications to robotic exploration and environmental monitoring. The International Journal of Robotics Research 38, 6 (2019), 658--685. https://doi.org/10.1177/0278364919844575 arXiv:https://doi.org/10.1177/0278364919844575Google ScholarDigital Library
- Shervin Javdani, J Andrew Bagnell, and Siddhartha S Srinivasa. 2016. Minimizing User Cost for Shared Autonomy. In 2016 11th ACM/IEEE International Conference on Human-Robot Interaction (HRI). IEEE, 621--622.Google Scholar
- Joshua D Knowles and David W Corne. 2000. Approximating the nondominated front using the Pareto archived evolution strategy. Evolutionary computation 8, 2 (2000), 149--172.Google Scholar
- Maria Koskinopoulou, Stylianos Piperakis, and Panos Trahanias. 2016. Learning from Demonstration Facilitates Human-Robot Collaborative Task Execution. In 2016 11th ACM/IEEE International Conference on Human-Robot Interaction (HRI). IEEE, 59--66.Google ScholarCross Ref
- Arun Kumar, Mason Bell, Benjamin Mellinkoff, Alex Sandoval, Wendy Bailey Martin, and Jack Burns. 2020. A Methodology to Assess the Human Factors Associated with Lunar Teleoperated Assembly Tasks. In 2020 IEEE Aerospace Conference. IEEE, 1--12.Google ScholarCross Ref
- Ruisen Liu, Matthew C Gombolay, and Stephen Balakirsky. 2021. Torwards Unpaired Human-to-Robot Demonstration Translation Learning Novel Tasks. In ICSR Workshop Human Robot Interaction for Space Robotics (HRI-SR).Google Scholar
- Ruisen Liu, Manisha Natarajan, and Matthew C. Gombolay. 2021. Coordinating Human-Robot Teams with Dynamic and Stochastic Task Proficiencies. J. Hum.- Robot Interact. 11, 1, Article 5 (oct 2021), 42 pages. https://doi.org/10.1145/3477391Google ScholarDigital Library
- Shipeng Liu, Cristina G Wilson, Bhaskar Krishnamachari, and Feifei Qian. 2023. Understanding Human Dynamic Sampling Objectives to Enable Robot-assisted Scientific Decision Making. ACM Transactions on Human-Robot Interaction (2023).Google Scholar
- R. T. Marler and J. S. Arora. 2004. Survey of multi-objective optimization methods for engineering. Structural and Multidisciplinary Optimization 26, 6 (01 Apr 2004), 369--395. https://doi.org/10.1007/s00158-003-0368--6Google ScholarCross Ref
- Jeremy A. Marvel, Shelly Bagchi, Megan Zimmerman, Murat Aksu, Brian Antonishek, Yue Wang, Ross Mead, Terry Fong, and Heni Ben Amor. 2022. Introduction to the Special Issue on Test Methods for Human-Robot Teaming Performance Evaluations. J. Hum.-Robot Interact. 11, 3, Article 22 (sep 2022), 5 pages. https://doi.org/10.1145/3544303Google ScholarDigital Library
- C McKenna-Neuman and WG Nickling. 1989. A theoretical and wind tunnel investigation of the effect of capillary water on the entrainment of sediment by wind. Canadian Journal of Soil Science 69, 1 (1989), 79--96.Google ScholarCross Ref
- Debasmita Mukherjee, Kashish Gupta, Li Hsin Chang, and Homayoun Najjaran. 2022. A Survey of Robot Learning Strategies for Human-Robot Collaboration in Industrial Settings. Robotics and Computer-Integrated Manufacturing 73 (2022), 102231.Google ScholarDigital Library
- Stefanos Nikolaidis and Julie Shah. 2013. Human-Robot Cross-Training: Computational Formulation, Modeling and Evaluation of a Human Team Training Strategy. In 2013 8th ACM/IEEE International Conference on Human-Robot Interaction (HRI). IEEE, 33--40.Google ScholarCross Ref
- Petter Nilsson, Sofie Haesaert, Rohan Thakker, Kyohei Otsu, Cristian-Ioan Vasile, Ali-Akbar Agha-Mohammadi, Richard M Murray, and Aaron D Ames. 2018. Toward specification-guided active mars exploration for cooperative robot teams. (2018).Google Scholar
- Darren Pais, PatrickMHogan, Thomas Schlegel, Nigel R Franks, Naomi E Leonard, and James AR Marshall. 2013. A mechanism for value-sensitive decision-making. PloS one 8, 9 (2013), e73216.Google ScholarCross Ref
- G. Picardi, M. Chellapurath, S. Iacoponi, S. Stefanni, C. Laschi, and M. Calisti. 2020. Bioinspired underwater legged robot for seabed exploration with low environmental disturbance. Science Robotics 5, 42 (2020), eaaz1012. https://doi.org/10.1126/scirobotics.aaz1012 arXiv:https://www.science.org/doi/pdf/10.1126/scirobotics.aaz1012Google ScholarCross Ref
- Eric A Pilles, M Cross, CM Caudill, R Francis, GR Osinski, J Newman, M Battler, M Bourassa, T Haltigin, V Hipkin, et al. 2019. Exploring ew models for improving planetary rover operations efficiency through the 2016 CanMars Mars Sample Return (MSR) analogue deployment. Planetary and Space Science 165 (2019), 250--259.Google ScholarCross Ref
- Feifei Qian, Douglas Jerolmack, Nicholas Lancaster, George Nikolich, Paul Reverdy, Sonia Roberts, Thomas Shipley, R Scott Van Pelt, Ted M Zobeck, and Daniel E Koditschek. 2017. Ground robotic measurement of aeolian processes. Aeolian research 27 (2017), 1--11.Google Scholar
- Feifei Qian, Dylan Lee, George Nikolich, Daniel Koditschek, and Douglas Jerolmack. 2019. Rapid In Situ Characterization of Soil Erodibility With a Field Deployable Robot. Journal of Geophysical Research: Earth Surface 124, 5 (2019), 1261--1280.Google ScholarCross Ref
- DiederikMRoijers, Peter Vamplew, Shimon Whiteson, and Richard Dazeley. 2013. A survey of multi-objective sequential decision-making. Journal of Artificial Intelligence Research 48 (2013), 67--113.Google ScholarCross Ref
- Sushil Kumar Sahoo and Shankha Shubhra Goswami. 2023. A Comprehensive Review of Multiple Criteria Decision-Making (MCDM) Methods: Advancements, Applications, and Future Directions. Decision Making Advances 1, 1 (Jun. 2023), 25--48. https://doi.org/10.31181/dma1120237Google ScholarCross Ref
- Uluc Saranli, Martin Buehler, and Daniel E Koditschek. 2001. RHex: A simple and highly mobile hexapod robot. The International Journal of Robotics Research 20, 7 (2001), 616--631.Google ScholarCross Ref
- Erik L Seedhouse and Pedro Llanos. 2021. Science and exploration of the moon enabled by surface telerobotics. Journal of Space Safety Engineering 8, 3 (2021), 231--237.Google ScholarCross Ref
- Thomas D Seeley, P Kirk Visscher, Thomas Schlegel, Patrick M Hogan, Nigel R Franks, and James AR Marshall. 2012. Stop signals provide cross inhibition in collective decision-making by honeybee swarms. Science 335, 6064 (2012), 108--111.Google ScholarCross Ref
- Florian Shkurti, Anqi Xu, Malika Meghjani, Juan Camilo, Juan Higuera, Yogesh Girdhar, Philippe Giguère, Bir Dey, Jimmy Li, Arnold Kalmbach, Chris Prahacs, Katrine Turgeon, Ioannis Rekleitis, and Gregory Dudek. 2012. Multi-Domain Monitoring of Marine Environments using a Heterogeneous Robot Team. https:Google Scholar
- Thane Somers and Geoffrey A Hollinger. 2014. Coactive Learning with a Human Expert for Robotic Monitoring. In Workshop on Robotic Monitoring at Robotics Science and Systems, Vol. 2014. 1--2.Google Scholar
- Mehrdad Tamiz, Dylan Jones, and Carlos Romero. 1998. Goal programming for decision making: An overview of the current state-of-the-art. European Journal of Operational Research 111, 3 (1998), 569--581. https://doi.org/10.1016/S0377- 2217(97)00317--2Google ScholarCross Ref
- Paul FMJ Verschure and Philipp Althaus. 2003. A real-world rational agent: unifying old and new AI. Cognitive science 27, 4 (2003), 561--590.Google Scholar
- Nils Wilde, Alexandru Blidaru, Stephen L Smith, and Dana Kulic. 2020. Improving user specifications for robot behavior through active preference learning: Framework and evaluation. The International Journal of Robotics Research 39, 6 (2020), 651--667. https://doi.org/10.1177/0278364920910802 arXiv:https://doi.org/10.1177/0278364920910802Google ScholarDigital Library
- Cristina G Wilson, Clare Elizabeth Bond, and Thomas F Shipley. 2019. How can geologic decision making under uncertainty be improved? Solid earth (2019), 1--34.Google Scholar
- Cristina G Wilson, Feifei Qian, Douglas J Jerolmack, Sonia Roberts, Jonathan Ham, Daniel Koditschek, and Thomas F Shipley. 2021. Spatially and temporally distributed data foraging decisions in disciplinary field science. Cognitive Research: Principles and Implications 6, 1 (2021), 1--16.Google ScholarCross Ref
- Yi Xiang, Yuren Zhou, Xiaowei Yang, and Han Huang. 2020. A Many-Objective Evolutionary Algorithm With Pareto-Adaptive Reference Points. IEEE Transactions on Evolutionary Computation 24, 1 (2020), 99--113. https://doi.org/10.1109/ TEVC.2019.2909636Google ScholarDigital Library
- R Aileen Yingst, Julie K Bartley, Thomas J Chidsey Jr, Barbara A Cohen, Brian M Hynek, Linda C Kah, Michelle E Minitti, Michael D Vanden Berg, Rebecca ME Williams, Madison Adams, et al. 2020. Is a Linear or a Walkabout Protocol More Efficient When Using a Rover to Choose Biologically Relevant Samples in a Small Region of Interest? Astrobiology 20, 3 (2020), 327--348.Google ScholarCross Ref
- Akib Zaman, Mohammad Shahjahan Majib, Shoeb Ahmed Tanjim, Shah Md Ahasan Siddique, Fardeen Ashraf, Shafayetul Islam, Abu Hena Md Maruf Morshed, Shadman Tajwar Shahid, Ishraq Hasan, Oliullah Samir, Safwan Shafquat, Naim Ibna Khadem Al Bhuyain, Asif Mahmud Rayhan,MD. Mushfik Ul Islam,MD. Akhtaruzzaman, and MD. Mahbubur Rahman. 2022. Phoenix: Towards designing and developing a human assistant rover. IEEE Access 10 (2022), 50728--50754.Google ScholarCross Ref
- Ruohan Zhang, Faraz Torabi, Garrett Warnell, and Peter Stone. 2021. Recent advances in leveraging human guidance for sequential decision-making tasks. Autonomous Agents and Multi-Agent Systems 35, 2 (2021), 31.Google ScholarDigital Library
- Yong Zheng and David (Xuejun) Wang. 2022. A survey of recommender systems with multi-objective optimization. Neurocomputing 474 (2022), 141--153. https: //doi.org/10.1016/j.neucom.2021.11.041Google ScholarDigital Library
- Aimin Zhou, Bo-Yang Qu, Hui Li, Shi-Zheng Zhao, Ponnuthurai Nagaratnam Suganthan, and Qingfu Zhang. 2011. Multiobjective evolutionary algorithms: A survey of the state of the art. Swarm and Evolutionary Computation 1, 1 (2011), 32--49. https://doi.org/10.1016/j.swevo.2011.03.001Google ScholarCross Ref
Index Terms
- Modelling Experts' Sampling Strategy to Balance Multiple Objectives During Scientific Explorations
Recommendations
Understanding Human Dynamic Sampling Objectives to Enable Robot-assisted Scientific Decision Making
Truly collaborative scientific field data collection between human scientists and autonomous robot systems requires a shared understanding of the search objectives and tradeoffs faced when making decisions. Therefore, critical to developing intelligent ...
Generating Objectives: Can Decision Makers Articulate What They Want?
Objectives have long been considered a basis for sound decision making. This research examines the ability of decision makers to generate self-relevant objectives for consequential decisions. In three empirical studies, participants consistently omitted ...
Pruned Pareto-optimal sets for the system redundancy allocation problem based on multiple prioritized objectives
In this paper, a new methodology is presented to solve different versions of multi-objective system redundancy allocation problems with prioritized objectives. Multi-objective problems are often solved by modifying them into equivalent single objective ...
Comments