--- _id: '1097' abstract: - lang: eng text: We present an interactive system for computational design, optimization, and fabrication of multicopters. Our computational approach allows non-experts to design, explore, and evaluate a wide range of different multicopters. We provide users with an intuitive interface for assembling a multicopter from a collection of components (e.g., propellers, motors, and carbon fiber rods). Our algorithm interactively optimizes shape and controller parameters of the current design to ensure its proper operation. In addition, we allow incorporating a variety of other metrics (such as payload, battery usage, size, and cost) into the design process and exploring tradeoffs between them. We show the efficacy of our method and system by designing, optimizing, fabricating, and operating multicopters with complex geometries and propeller configurations. We also demonstrate the ability of our optimization algorithm to improve the multicopter performance under different metrics. acknowledgement: "We thank Nobuyuki Umetani for his insightful suggestions in our discussions. We thank Alan Schultz and his colleagues at NRL for building the hexacopter and for the valuable discussions. We thank Randall Davis, Boris Katz, and Howard Shrobe at MIT for their advice. We are grateful to Nick Bandiera for preprocessing mechanical parts and providing 3D printing technical support; Charles Blouin from RCBenchmark for dynamometer hardware support; Brian Saavedra for the composition UI; Yingzhe Yuan for data acquisition and video recording in the experiments; Michael Foshey and David Kim for their comments on the draft of the paper. \r\n\r\n\r\nThis work was partially supported by Air Force Research Laboratory’s sponsorship of Julia: A Fresh Approach to Technical Computing and Data Processing (Sponsor Award ID FA8750-15-2- 0272, MIT Award ID 024831-00003), and NSF Expedition project (Sponsor Award ID CCF-1138967, MIT Award ID 020610-00002). The views expressed herein are not endorsed by the sponsors. This project has also received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 645599. " alternative_title: - ACM Transactions on Graphics article_number: '227' author: - first_name: Tao full_name: Du, Tao last_name: Du - first_name: Adriana full_name: Schulz, Adriana last_name: Schulz - first_name: Bo full_name: Zhu, Bo last_name: Zhu - first_name: Bernd full_name: Bickel, Bernd id: 49876194-F248-11E8-B48F-1D18A9856A87 last_name: Bickel orcid: 0000-0001-6511-9385 - first_name: Wojciech full_name: Matusik, Wojciech last_name: Matusik citation: ama: 'Du T, Schulz A, Zhu B, Bickel B, Matusik W. Computational multicopter design. In: Vol 35. ACM; 2016. doi:10.1145/2980179.2982427' apa: 'Du, T., Schulz, A., Zhu, B., Bickel, B., & Matusik, W. (2016). Computational multicopter design (Vol. 35). Presented at the SIGGRAPH Asia: Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia, Macao, China: ACM. https://doi.org/10.1145/2980179.2982427' chicago: Du, Tao, Adriana Schulz, Bo Zhu, Bernd Bickel, and Wojciech Matusik. “Computational Multicopter Design,” Vol. 35. ACM, 2016. https://doi.org/10.1145/2980179.2982427. ieee: 'T. Du, A. Schulz, B. Zhu, B. Bickel, and W. Matusik, “Computational multicopter design,” presented at the SIGGRAPH Asia: Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia, Macao, China, 2016, vol. 35, no. 6.' ista: 'Du T, Schulz A, Zhu B, Bickel B, Matusik W. 2016. Computational multicopter design. SIGGRAPH Asia: Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia, ACM Transactions on Graphics, vol. 35, 227.' mla: Du, Tao, et al. Computational Multicopter Design. Vol. 35, no. 6, 227, ACM, 2016, doi:10.1145/2980179.2982427. short: T. Du, A. Schulz, B. Zhu, B. Bickel, W. Matusik, in:, ACM, 2016. conference: end_date: 2016-12-08 location: Macao, China name: 'SIGGRAPH Asia: Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia' start_date: 2016-12-05 date_created: 2018-12-11T11:50:07Z date_published: 2016-11-01T00:00:00Z date_updated: 2021-01-12T06:48:15Z day: '01' ddc: - '006' department: - _id: BeBi doi: 10.1145/2980179.2982427 ec_funded: 1 file: - access_level: open_access content_type: application/pdf creator: system date_created: 2018-12-12T10:17:42Z date_updated: 2018-12-12T10:17:42Z file_id: '5298' file_name: IST-2017-759-v1+1_copter.pdf file_size: 33114420 relation: main_file file_date_updated: 2018-12-12T10:17:42Z has_accepted_license: '1' intvolume: ' 35' issue: '6' language: - iso: eng month: '11' oa: 1 oa_version: Submitted Version project: - _id: 25082902-B435-11E9-9278-68D0E5697425 call_identifier: H2020 grant_number: '645599' name: Soft-bodied intelligence for Manipulation publication_status: published publisher: ACM publist_id: '6278' pubrep_id: '759' quality_controlled: '1' scopus_import: 1 status: public title: Computational multicopter design type: conference user_id: 3E5EF7F0-F248-11E8-B48F-1D18A9856A87 volume: 35 year: '2016' ... --- _id: '1098' abstract: - lang: eng text: Better understanding of the potential benefits of information transfer and representation learning is an important step towards the goal of building intelligent systems that are able to persist in the world and learn over time. In this work, we consider a setting where the learner encounters a stream of tasks but is able to retain only limited information from each encountered task, such as a learned predictor. In contrast to most previous works analyzing this scenario, we do not make any distributional assumptions on the task generating process. Instead, we formulate a complexity measure that captures the diversity of the observed tasks. We provide a lifelong learning algorithm with error guarantees for every observed task (rather than on average). We show sample complexity reductions in comparison to solving every task in isolation in terms of our task complexity measure. Further, our algorithmic framework can naturally be viewed as learning a representation from encountered tasks with a neural network. acknowledgement: "This work was in parts funded by the European Research Council under the European Union’s Seventh Framework Programme (FP7/2007-2013)/ERC grant agreement no 308036.\r\n\r\n" alternative_title: - Advances in Neural Information Processing Systems author: - first_name: Anastasia full_name: Pentina, Anastasia id: 42E87FC6-F248-11E8-B48F-1D18A9856A87 last_name: Pentina - first_name: Ruth full_name: Urner, Ruth last_name: Urner citation: ama: 'Pentina A, Urner R. Lifelong learning with weighted majority votes. In: Vol 29. Neural Information Processing Systems; 2016:3619-3627.' apa: 'Pentina, A., & Urner, R. (2016). Lifelong learning with weighted majority votes (Vol. 29, pp. 3619–3627). Presented at the NIPS: Neural Information Processing Systems, Barcelona, Spain: Neural Information Processing Systems.' chicago: Pentina, Anastasia, and Ruth Urner. “Lifelong Learning with Weighted Majority Votes,” 29:3619–27. Neural Information Processing Systems, 2016. ieee: 'A. Pentina and R. Urner, “Lifelong learning with weighted majority votes,” presented at the NIPS: Neural Information Processing Systems, Barcelona, Spain, 2016, vol. 29, pp. 3619–3627.' ista: 'Pentina A, Urner R. 2016. Lifelong learning with weighted majority votes. NIPS: Neural Information Processing Systems, Advances in Neural Information Processing Systems, vol. 29, 3619–3627.' mla: Pentina, Anastasia, and Ruth Urner. Lifelong Learning with Weighted Majority Votes. Vol. 29, Neural Information Processing Systems, 2016, pp. 3619–27. short: A. Pentina, R. Urner, in:, Neural Information Processing Systems, 2016, pp. 3619–3627. conference: end_date: 2016-12-10 location: Barcelona, Spain name: 'NIPS: Neural Information Processing Systems' start_date: 2016-12-05 date_created: 2018-12-11T11:50:08Z date_published: 2016-12-01T00:00:00Z date_updated: 2021-01-12T06:48:15Z day: '01' ddc: - '006' department: - _id: ChLa ec_funded: 1 file: - access_level: open_access content_type: application/pdf creator: system date_created: 2018-12-12T10:12:42Z date_updated: 2018-12-12T10:12:42Z file_id: '4961' file_name: IST-2017-775-v1+1_main.pdf file_size: 237111 relation: main_file - access_level: open_access content_type: application/pdf creator: system date_created: 2018-12-12T10:12:43Z date_updated: 2018-12-12T10:12:43Z file_id: '4962' file_name: IST-2017-775-v1+2_supplementary.pdf file_size: 185818 relation: main_file file_date_updated: 2018-12-12T10:12:43Z has_accepted_license: '1' intvolume: ' 29' language: - iso: eng month: '12' oa: 1 oa_version: Published Version page: 3619-3627 project: - _id: 2532554C-B435-11E9-9278-68D0E5697425 call_identifier: FP7 grant_number: '308036' name: Lifelong Learning of Visual Scene Understanding publication_status: published publisher: Neural Information Processing Systems publist_id: '6277' pubrep_id: '775' quality_controlled: '1' scopus_import: 1 status: public title: Lifelong learning with weighted majority votes type: conference user_id: 3E5EF7F0-F248-11E8-B48F-1D18A9856A87 volume: 29 year: '2016' ... --- _id: '1099' abstract: - lang: eng text: We present FlexMolds, a novel computational approach to automatically design flexible, reusable molds that, once 3D printed, allow us to physically fabricate, by means of liquid casting, multiple copies of complex shapes with rich surface details and complex topology. The approach to design such flexible molds is based on a greedy bottom-up search of possible cuts over an object, evaluating for each possible cut the feasibility of the resulting mold. We use a dynamic simulation approach to evaluate candidate molds, providing a heuristic to generate forces that are able to open, detach, and remove a complex mold from the object it surrounds. We have tested the approach with a number of objects with nontrivial shapes and topologies. acknowledgement: "The armadillo, bunny and dragon models are courtesy of the Stanford \ 3D Scanning Repository. The bimba, fertility and elephant models are courtesy of the AIM@SHAPE Shape Repository. \r\nThis project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant \ agreement\r\nNo. 645599." alternative_title: - ACM Transactions on Graphics article_number: '223' author: - first_name: Luigi full_name: Malomo, Luigi last_name: Malomo - first_name: Nico full_name: Pietroni, Nico last_name: Pietroni - first_name: Bernd full_name: Bickel, Bernd id: 49876194-F248-11E8-B48F-1D18A9856A87 last_name: Bickel orcid: 0000-0001-6511-9385 - first_name: Paolo full_name: Cignoni, Paolo last_name: Cignoni citation: ama: 'Malomo L, Pietroni N, Bickel B, Cignoni P. FlexMolds: Automatic design of flexible shells for molding. In: Vol 35. ACM; 2016. doi:10.1145/2980179.2982397' apa: 'Malomo, L., Pietroni, N., Bickel, B., & Cignoni, P. (2016). FlexMolds: Automatic design of flexible shells for molding (Vol. 35). Presented at the SIGGRAPH Asia: Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia, Macao, China: ACM. https://doi.org/10.1145/2980179.2982397' chicago: 'Malomo, Luigi, Nico Pietroni, Bernd Bickel, and Paolo Cignoni. “FlexMolds: Automatic Design of Flexible Shells for Molding,” Vol. 35. ACM, 2016. https://doi.org/10.1145/2980179.2982397.' ieee: 'L. Malomo, N. Pietroni, B. Bickel, and P. Cignoni, “FlexMolds: Automatic design of flexible shells for molding,” presented at the SIGGRAPH Asia: Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia, Macao, China, 2016, vol. 35, no. 6.' ista: 'Malomo L, Pietroni N, Bickel B, Cignoni P. 2016. FlexMolds: Automatic design of flexible shells for molding. SIGGRAPH Asia: Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia, ACM Transactions on Graphics, vol. 35, 223.' mla: 'Malomo, Luigi, et al. FlexMolds: Automatic Design of Flexible Shells for Molding. Vol. 35, no. 6, 223, ACM, 2016, doi:10.1145/2980179.2982397.' short: L. Malomo, N. Pietroni, B. Bickel, P. Cignoni, in:, ACM, 2016. conference: end_date: 2016-12-08 location: Macao, China name: 'SIGGRAPH Asia: Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia' start_date: 2016-12-05 date_created: 2018-12-11T11:50:08Z date_published: 2016-11-01T00:00:00Z date_updated: 2021-01-12T06:48:16Z day: '01' ddc: - '000' - '005' department: - _id: BeBi doi: 10.1145/2980179.2982397 ec_funded: 1 file: - access_level: open_access content_type: application/pdf creator: system date_created: 2018-12-12T10:12:01Z date_updated: 2018-12-12T10:12:01Z file_id: '4918' file_name: IST-2017-760-v1+1_flexmolds.pdf file_size: 11122029 relation: main_file file_date_updated: 2018-12-12T10:12:01Z has_accepted_license: '1' intvolume: ' 35' issue: '6' language: - iso: eng month: '11' oa: 1 oa_version: Submitted Version project: - _id: 25082902-B435-11E9-9278-68D0E5697425 call_identifier: H2020 grant_number: '645599' name: Soft-bodied intelligence for Manipulation publication_status: published publisher: ACM publist_id: '6276' pubrep_id: '760' quality_controlled: '1' scopus_import: 1 status: public title: 'FlexMolds: Automatic design of flexible shells for molding' type: conference user_id: 3E5EF7F0-F248-11E8-B48F-1D18A9856A87 volume: 35 year: '2016' ... --- _id: '1102' abstract: - lang: eng text: Weakly-supervised object localization methods tend to fail for object classes that consistently co-occur with the same background elements, e.g. trains on tracks. We propose a method to overcome these failures by adding a very small amount of model-specific additional annotation. The main idea is to cluster a deep network\'s mid-level representations and assign object or distractor labels to each cluster. Experiments show substantially improved localization results on the challenging ILSVC2014 dataset for bounding box detection and the PASCAL VOC2012 dataset for semantic segmentation. acknowledgement: "This work was funded in parts by the European Research Council\r\nunder the European Union’s Seventh Framework Programme (FP7/2007-2013)/ERC grant\r\nagreement no 308036. We gratefully acknowledge the support of NVIDIA Corporation with\r\nthe donation of the GPUs used for this research." author: - first_name: Alexander full_name: Kolesnikov, Alexander id: 2D157DB6-F248-11E8-B48F-1D18A9856A87 last_name: Kolesnikov - first_name: Christoph full_name: Lampert, Christoph id: 40C20FD2-F248-11E8-B48F-1D18A9856A87 last_name: Lampert orcid: 0000-0001-8622-7887 citation: ama: 'Kolesnikov A, Lampert C. Improving weakly-supervised object localization by micro-annotation. In: Proceedings of the British Machine Vision Conference 2016. Vol 2016-September. BMVA Press; 2016:92.1-92.12. doi:10.5244/C.30.92' apa: 'Kolesnikov, A., & Lampert, C. (2016). Improving weakly-supervised object localization by micro-annotation. In Proceedings of the British Machine Vision Conference 2016 (Vol. 2016–September, p. 92.1-92.12). York, United Kingdom: BMVA Press. https://doi.org/10.5244/C.30.92' chicago: Kolesnikov, Alexander, and Christoph Lampert. “Improving Weakly-Supervised Object Localization by Micro-Annotation.” In Proceedings of the British Machine Vision Conference 2016, 2016–September:92.1-92.12. BMVA Press, 2016. https://doi.org/10.5244/C.30.92. ieee: A. Kolesnikov and C. Lampert, “Improving weakly-supervised object localization by micro-annotation,” in Proceedings of the British Machine Vision Conference 2016, York, United Kingdom, 2016, vol. 2016–September, p. 92.1-92.12. ista: 'Kolesnikov A, Lampert C. 2016. Improving weakly-supervised object localization by micro-annotation. Proceedings of the British Machine Vision Conference 2016. BMVC: British Machine Vision Conference vol. 2016–September, 92.1-92.12.' mla: Kolesnikov, Alexander, and Christoph Lampert. “Improving Weakly-Supervised Object Localization by Micro-Annotation.” Proceedings of the British Machine Vision Conference 2016, vol. 2016–September, BMVA Press, 2016, p. 92.1-92.12, doi:10.5244/C.30.92. short: A. Kolesnikov, C. Lampert, in:, Proceedings of the British Machine Vision Conference 2016, BMVA Press, 2016, p. 92.1-92.12. conference: end_date: 2016-09-22 location: York, United Kingdom name: 'BMVC: British Machine Vision Conference' start_date: 2016-09-19 date_created: 2018-12-11T11:50:09Z date_published: 2016-09-01T00:00:00Z date_updated: 2021-01-12T06:48:18Z day: '01' department: - _id: ChLa doi: 10.5244/C.30.92 ec_funded: 1 language: - iso: eng main_file_link: - open_access: '1' url: http://www.bmva.org/bmvc/2016/papers/paper092/paper092.pdf month: '09' oa: 1 oa_version: Published Version page: 92.1-92.12 project: - _id: 2532554C-B435-11E9-9278-68D0E5697425 call_identifier: FP7 grant_number: '308036' name: Lifelong Learning of Visual Scene Understanding publication: Proceedings of the British Machine Vision Conference 2016 publication_status: published publisher: BMVA Press publist_id: '6273' quality_controlled: '1' scopus_import: 1 status: public title: Improving weakly-supervised object localization by micro-annotation type: conference user_id: 3E5EF7F0-F248-11E8-B48F-1D18A9856A87 volume: 2016-September year: '2016' ... --- _id: '1103' abstract: - lang: eng text: We propose two parallel state-space-exploration algorithms for hybrid automaton (HA), with the goal of enhancing performance on multi-core shared-memory systems. The first uses the parallel, breadth-first-search algorithm (PBFS) of the SPIN model checker, when traversing the discrete modes of the HA, and enhances it with a parallel exploration of the continuous states within each mode. We show that this simple-minded extension of PBFS does not provide the desired load balancing in many HA benchmarks. The second algorithm is a task-parallel BFS algorithm (TP-BFS), which uses a cheap precomputation of the cost associated with the post operations (both continuous and discrete) in order to improve load balancing. We illustrate the TP-BFS and the cost precomputation of the post operators on a support-function-based algorithm for state-space exploration. The performance comparison of the two algorithms shows that, in general, TP-BFS provides a better utilization/load-balancing of the CPU. Both algorithms are implemented in the model checker XSpeed. Our experiments show a maximum speed-up of more than 2000 χ on a navigation benchmark, with respect to SpaceEx LGG scenario. In order to make the comparison fair, we employed an equal number of post operations in both tools. To the best of our knowledge, this paper represents the first attempt to provide parallel, reachability-analysis algorithms for HA. acknowledgement: This work was supported in part by DST-SERB, GoI under Project No. YSS/2014/000623 and by the European Research Council (ERC) under grant 267989 (QUAREM) and by the Austrian Science Fund (FWF) under grants S11402-N23, S11405-N23 and S11412-N23 (RiSE/SHiNE) and Z211-N23 (Wittgenstein Award). article_number: '7797741' author: - first_name: Amit full_name: Gurung, Amit last_name: Gurung - first_name: Arup full_name: Deka, Arup last_name: Deka - first_name: Ezio full_name: Bartocci, Ezio last_name: Bartocci - first_name: Sergiy full_name: Bogomolov, Sergiy id: 369D9A44-F248-11E8-B48F-1D18A9856A87 last_name: Bogomolov orcid: 0000-0002-0686-0365 - first_name: Radu full_name: Grosu, Radu last_name: Grosu - first_name: Rajarshi full_name: Ray, Rajarshi last_name: Ray citation: ama: 'Gurung A, Deka A, Bartocci E, Bogomolov S, Grosu R, Ray R. Parallel reachability analysis for hybrid systems. In: IEEE; 2016. doi:10.1109/MEMCOD.2016.7797741' apa: 'Gurung, A., Deka, A., Bartocci, E., Bogomolov, S., Grosu, R., & Ray, R. (2016). Parallel reachability analysis for hybrid systems. Presented at the MEMOCODE: International Conference on Formal Methods and Models for System Design, Kanpur, India : IEEE. https://doi.org/10.1109/MEMCOD.2016.7797741' chicago: Gurung, Amit, Arup Deka, Ezio Bartocci, Sergiy Bogomolov, Radu Grosu, and Rajarshi Ray. “Parallel Reachability Analysis for Hybrid Systems.” IEEE, 2016. https://doi.org/10.1109/MEMCOD.2016.7797741. ieee: 'A. Gurung, A. Deka, E. Bartocci, S. Bogomolov, R. Grosu, and R. Ray, “Parallel reachability analysis for hybrid systems,” presented at the MEMOCODE: International Conference on Formal Methods and Models for System Design, Kanpur, India , 2016.' ista: 'Gurung A, Deka A, Bartocci E, Bogomolov S, Grosu R, Ray R. 2016. Parallel reachability analysis for hybrid systems. MEMOCODE: International Conference on Formal Methods and Models for System Design, 7797741.' mla: Gurung, Amit, et al. Parallel Reachability Analysis for Hybrid Systems. 7797741, IEEE, 2016, doi:10.1109/MEMCOD.2016.7797741. short: A. Gurung, A. Deka, E. Bartocci, S. Bogomolov, R. Grosu, R. Ray, in:, IEEE, 2016. conference: end_date: 2016-11-20 location: 'Kanpur, India ' name: 'MEMOCODE: International Conference on Formal Methods and Models for System Design' start_date: 2016-11-18 date_created: 2018-12-11T11:50:09Z date_published: 2016-12-27T00:00:00Z date_updated: 2021-01-12T06:48:18Z day: '27' department: - _id: ToHe doi: 10.1109/MEMCOD.2016.7797741 ec_funded: 1 language: - iso: eng main_file_link: - open_access: '1' url: https://arxiv.org/abs/1606.05473 month: '12' oa: 1 oa_version: Preprint project: - _id: 25EE3708-B435-11E9-9278-68D0E5697425 call_identifier: FP7 grant_number: '267989' name: Quantitative Reactive Modeling - _id: 25F42A32-B435-11E9-9278-68D0E5697425 call_identifier: FWF grant_number: Z211 name: The Wittgenstein Prize - _id: 25832EC2-B435-11E9-9278-68D0E5697425 call_identifier: FWF grant_number: S 11407_N23 name: Rigorous Systems Engineering publication_status: published publisher: IEEE publist_id: '6272' quality_controlled: '1' scopus_import: 1 status: public title: Parallel reachability analysis for hybrid systems type: conference user_id: 3E5EF7F0-F248-11E8-B48F-1D18A9856A87 year: '2016' ...