{"type":"ScholarlyArticle","title":"Reliable Neuro-Symbolic Abstractions for Planning and Learning","authors":[{"name":"Naman Shah","slug":"naman-shah","given":"Naman","family":"Shah","affiliation":"Arizona State University , Tempe , AZ , USA"}],"abstract":"Although state-of-the-art hierarchical robot planning algorithms allow robots to efficiently compute long-horizon motion plans for achieving user desired tasks, these methods typically rely upon environment-dependent state and action abstractions that need to be hand-designed by experts. On the other hand, non-hierarchical robot planning approaches fail to compute solutions for complex tasks that require reasoning over a long horizon. My research addresses these problems by proposing an approach for learning abstractions and developing hierarchical planners that efficiently use learned abstractions to boost robot planning performance and provide strong guarantees of reliability.","doi":"10.24963/ijcai.2023/821","url":"https://ijcai.org/proceedings/2023/821","pdf":"https://ijcai.org/proceedings/2023/0821.pdf","markdown":"https://ijcai.org/proceedings/2023/821.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/821","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"Doctoral Consortium","track":"Doctoral Consortium","number":821,"pages":{"first":7093,"last":7094},"keywords":["Planning and Scheduling: PS: Robot planning","Planning and Scheduling: PS: Learning in planning and scheduling","Robotics: ROB: Learning in robotics","Planning and Scheduling: PS: Hierarchical planning","Robotics: ROB: Motion and path planning","Planning and Scheduling: PS: Planning under uncertainty"],"videos":[],"references":[{"position":1,"raw":"[Bagaria and Konidaris, 2020] A. Bagaria and G. Konidaris. Option discovery using deep skill chaining. In ICLR, 2020.","title":"Option discovery using deep skill chaining","authors":"A Bagaria, G Konidaris","year":"2020","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Dantam et al., 2018] N. Dantam, Z. Kingston, and S. Chaud- huriand L. Kavraki. An incremental constraint-based framework for task and motion planning. IJRR, 37(10):1134-1151, 2018.","title":"An incremental constraint-based framework for task and motion planning","authors":"N Dantam, Z Kingston, S Chaudhuriand, L Kavraki","year":"2018","venue":"IJRR","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Garrett et al., 2020] C. Garrett, T. Lozano-Pérez, and L. Kaelbling. PDDLStream: Integrating symbolic planners and blackbox sam- plers via optimistic adaptive planning. In ICAPS, 2020.","title":"PDDLStream: Integrating symbolic planners and blackbox samplers via optimistic adaptive planning","authors":"C Garrett, T Lozano-Pérez, L Kaelbling","year":"2020","venue":"ICAPS","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Haarnoja et al., 2018] T. Haarnoja, A. Zhou, P. Abbeel, and S. Levine. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In ICML, 2018.","title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","authors":"T Haarnoja, A Zhou, P Abbeel, S Levine","year":"2018","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Kavraki et al., 1996] LE. Kavraki, P. Svestka, J-C Latombe, and MH. Overmars. Probabilistic roadmaps for path planning in high- dimensional configuration spaces. IEEE TRO, 12(4), 1996.","title":"Probabilistic roadmaps for path planning in highdimensional configuration spaces","authors":"Kavraki","year":"1996","venue":"IEEE TRO","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Kuffner and LaValle, 2000] JJ. Kuffner and SM. LaValle. Rrt- connect: An efficient approach to single-query path planning. In ICRA, 2000.","title":"Rrtconnect: An efficient approach to single-query path planning","authors":"Lavalle ; ] Jj Kuffner, S M Kuffner, Lavalle","year":"2000","venue":"ICRA","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Kurutach et al., 2018] T. Kurutach, A. Tamar, G. Yang SJ. Russell, and P. Abbeel. Learning plannable representations with causal InfoGANs. In NeruIPS, 2018.","title":"Learning plannable representations with causal InfoGANs","authors":"T Kurutach, A Tamar, G Yang, S J Russell, P Abbeel","year":"2018","venue":"NeruIPS","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[LaValle and others, 1998] Steven M LaValle et al. Rapidly- exploring random trees: A new tool for path planning. Iowa State University, 1998.","title":"Rapidlyexploring random trees: A new tool for path planning","authors":"Steven M Lavalle","year":"1998","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Lowerre, 1976] BT. Lowerre. The Harpy Speech Recognition Sys- tem. Carnegie Mellon University, 1976.","title":"The Harpy Speech Recognition System","authors":"; Lowerre, Bt, Lowerre","year":"1976","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Molina et al., 2020] D. Molina, K. Kumar, and S. Srivastava. Iden- tifying critical regions for motion planning using auto-generated saliency labels with convolutional neural networks. In ICRA, 2020.","title":"Identifying critical regions for motion planning using auto-generated saliency labels with convolutional neural networks","authors":"D Molina, K Kumar, S Srivastava","year":"2020","venue":"ICRA","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Shah and Srivastava, 2022a] N. Shah and S. Srivastava. Multi-task option learning and discovery for stochastic path planning. arXiv preprint arXiv:2210.00068, 2022.","title":"Multi-task option learning and discovery for stochastic path planning","authors":"Srivastava Shah, N Shah, S Srivastava","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Shah and Srivastava, 2022b] N. Shah and S. Srivastava. Using deep learning to bootstrap abstractions for hierarchical robot planning. In AAMAS, 2022.","title":"Using deep learning to bootstrap abstractions for hierarchical robot planning","authors":"Srivastava Shah, N Shah, S Srivastava","year":"2022","venue":"AAMAS","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Shah et al., 2020] N. Shah, D. Kala Vasudevan, K. Kumar, P. Kamojjhala, and S. Srivastava. Anytime integrated task and motion policies for stochastic environments. In ICRA, 2020.","title":"Anytime integrated task and motion policies for stochastic environments","authors":"N Shah, D Kala Vasudevan, K Kumar, P Kamojjhala, S Srivastava","year":"2020","venue":"ICRA","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}