Abstract
Differentiable planning network architecture has shown to be powerful in solving transfer planning tasks while it possesses a simple end-to-end training feature. Much related work that has been proposed in literature is inspired by a design principle in which a recursive network architecture is applied to emulate backup operations of a value iteration algorithm. However, existing frameworks can only learn and plan effectively on domains with a lattice structure, i.e., regular graphs embedded in a particular Euclidean space. In this paper, we propose a general planning network called Graph-based Motion Planning Networks (GrMPN). GrMPN will be able to i) learn and plan on general irregular graphs, hence ii) render existing planning network architectures special cases. The proposed GrMPN framework is invariant to task graph permutation, i.e., graph isomorphism. As a result, GrMPN possesses an ability that is data-efficient and strong at generalization strength. We demonstrate the performance of two proposed GrMPN methods against other baselines on three domains ranging from 2D mazes (regular graph), path planning on irregular graphs, and motion planning (an irregular graph of robot configurations).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Atwood, J., Towsley, D.: Diffusion-convolutional neural networks. In: NIPS, pp. 1993–2001 (2016)
Bajpai, A.N., Garg, S., et al.: Transfer of deep reactive policies for MDP planning. In: NIPS, pp. 10965–10975 (2018)
Battaglia, P.W., et al.: Relational inductive biases, deep learning, and graph networks. arXiv preprint arXiv:1806.01261 (2018)
Battaglia, P.W., Pascanu, R., Lai, M., Rezende, D.J., Kavukcuoglu, K.: Interaction networks for learning about objects, relations and physics. In: NIPS, pp. 4502–4510 (2016)
Bertsekas, D.P., Bertsekas, D.P., Bertsekas, D.P., Bertsekas, D.P.: Dynamic Programming and Optimal Control, vol. 1. Athena Scientific, Belmont (1995)
Bruna, J., Zaremba, W., Szlam, A., LeCun, Y.: Spectral networks and locally connected networks on graphs. arXiv preprint arXiv:1312.6203 (2013)
Duvenaud, D.K., et al.: Convolutional networks on graphs for learning molecular fingerprints. In: NIPS, pp. 2224–2232 (2015)
Gilmer, J., Schoenholz, S.S., Riley, P.F., Vinyals, O., Dahl, G.E.: Neural message passing for quantum chemistry. In: ICML, pp. 1263–1272 (2017)
Gupta, S., Davidson, J., Levine, S., Sukthankar, R., Malik, J.: Cognitive mapping and planning for visual navigation. In: CVPR, pp. 7272–7281 (2017)
Hagberg, A., Swart, P., S Chult, D.: Exploring network structure, dynamics, and function using network. Technical report, Los Alamos National Lab. (LANL), Los Alamos, NM, United States (2008)
Heess, N., Wayne, G., Silver, D., Lillicrap, T.P., Erez, T., Tassa, Y.: Learning continuous control policies by stochastic value gradients. In: NIPS, pp. 2944–2952 (2015)
Henaff, M., Bruna, J., LeCun, Y.: Deep convolutional networks on graph-structured data. arXiv preprint arXiv:1506.05163 (2015)
Karkus, P., Hsu, D., Lee, W.S.: QMDP-Net: deep learning for planning under partial observability. In: NIPS, pp. 4694–4704 (2017)
Kearnes, S., McCloskey, K., Berndl, M., Pande, V., Riley, P.: Molecular graph convolutions: moving beyond fingerprints. J. Comput. Aided Mol. Des. 30(8), 595–608 (2016). https://doi.org/10.1007/s10822-016-9938-8
Khan, A., Zhang, C., Atanasov, N., Karydis, K., Kumar, V., Lee, D.D.: Memory augmented control networks. In: ICLR (2018)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: ICLR (2017)
Kober, J., Bagnell, J.A., Peters, J.: Reinforcement learning in robotics: a survey. Int. J. Robot. Res. 32(11), 1238–1274 (2013)
Kurutach, T., Clavera, I., Duan, Y., Tamar, A., Abbeel, P.: Model-ensemble trust-region policy optimization. In: ICLR (2018)
LaValle, S.M.: Planning Algorithms. Cambridge University Press, Cambridge (2006)
Lee, G., Hou, B., Mandalika, A., Lee, J., Srinivasa, S.S.: Bayesian policy optimization for model uncertainty. arXiv preprint arXiv:1810.01014 (2018)
Lee, L., Parisotto, E., Chaplot, D.S., Xing, E., Salakhutdinov, R.: Gated path planning networks. arXiv preprint arXiv:1806.06408 (2018)
Levine, S., Finn, C., Darrell, T., Abbeel, P.: End-to-end training of deep visuomotor policies. J. Mach. Learn. Res. 17, 39:1–39:40 (2016)
Li, Y., Tarlow, D., Brockschmidt, M., Zemel, R.S.: Gated graph sequence neural networks. In: ICLR (2016)
Ma, T., Ferber, P., Huo, S., Chen, J., Katz, M.: Adaptive planner scheduling with graph neural networks. arXiv preprint arXiv:1811.00210 (2018)
Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529 (2015)
Niepert, M., Ahmed, M., Kutzkov, K.: Learning convolutional neural networks for graphs. In: ICML, pp. 2014–2023 (2016)
Niu, S., Chen, S., Guo, H., Targonski, C., Smith, M.C., Kovacevic, J.: Generalized value iteration networks: Life beyond lattices. In: AAAI, pp. 6246–6253. AAAI Press (2018)
Sanchez-Gonzalez, A., et al.: Graph networks as learnable physics engines for inference and control. arXiv preprint arXiv:1806.01242 (2018)
Scarselli, F., Gori, M., Tsoi, A.C., Hagenbuchner, M., Monfardini, G.: The graph neural network model. IEEE Trans. Neural Networks 20(1), 61–80 (2008)
Schütt, K.T., Arbabzadah, F., Chmiela, S., Müller, K.R., Tkatchenko, A.: Quantum-chemical insights from deep tensor neural networks. Nat. Commun. 8, 13890 (2017)
Segler, M., Preuß, M., Waller, M.P.: Towards “AlphaChem”: chemical synthesis planning with tree search and deep neural network policies. arXiv preprint arXiv:1702.00020 (2017)
Silver, D., et al.: The predictron: End-to-end learning and planning. In: ICML, pp. 3191–3199 (2017)
Silver, D., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484–489 (2016)
Srinivas, A., Jabri, A., Abbeel, P., Levine, S., Finn, C.: Universal planning networks: learning generalizable representations for visuomotor control. In: ICML, pp. 4739–4748 (2018)
Sutton, R.S., Barto, A.G., et al.: Introduction to Reinforcement Learning, vol. 2. MIT Press, Cambridge (1998)
Tamar, A., Levine, S., Abbeel, P., Wu, Y., Thomas, G.: Value iteration networks. In: NIPS, pp. 2146–2154 (2016)
Toyer, S., Trevizan, F., Thiébaux, S., Xie, L.: Action schema networks: generalised policies with deep learning. In: AAAI (2018)
Velickovic, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., Bengio, Y.: Graph attention networks. In: ICLR (2018)
Weisfeiler, B., Lehman, A.A.: A reduction of a graph to a canonical form and an algebra arising during this reduction. Nauchno-Technicheskaya Informatsia 2(9), 12–16 (1968)
Zhang, S., Yao, L., Sun, A., Tay, Y.: Deep learning based recommender system: a survey and new perspectives. ACM Comput. Surv. (CSUR) 52(1), 5 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Hoang, T., Vien, N.A. (2021). Graph-Based Motion Planning Networks. In: Hutter, F., Kersting, K., Lijffijt, J., Valera, I. (eds) Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2020. Lecture Notes in Computer Science(), vol 12458. Springer, Cham. https://doi.org/10.1007/978-3-030-67661-2_33
Download citation
DOI: https://doi.org/10.1007/978-3-030-67661-2_33
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-67660-5
Online ISBN: 978-3-030-67661-2
eBook Packages: Computer ScienceComputer Science (R0)