Filters








739 Hits in 2.4 sec

Algorithms and Insights for RaceTrack

Michael Bekos, Henry Förster, Michael Kaufmann, Simon Poschenrieder, Thomas Stüber
unpublished
We discuss algorithmic issues on the well-known paper-and-pencil game RaceTrack.  ...  We present and experimentally evaluate efficient algorithms for single player scenarios.  ...  The authors would like to thank Stefan Feil, Denis Heid, Tobias Kaulich, and Sotirios Pavlidis for developing the user interface of our prototype.  ... 
fatcat:dr4vpyjdpnd6fl6lq7na5i725y

A Fast Approach to Minimum Curvature Raceline Planning via Probabilistic Inference [article]

Salman Bari, Ahmad Schoha Haidari, Dirk Wollherr
2022 arXiv   pre-print
The proposed framework is evaluated for different racetracks and benchmark results are presented highlighting the computational efficiency, lap time and resulting raceline.  ...  faster algorithm.  ...  Human-Robot RECYcling plant for electriCal and eLEctRonic equipment".  ... 
arXiv:2203.03224v1 fatcat:42rqtsn7jvatrmnmvj4u3zytfq

Tracking the Race Between Deep Reinforcement Learning and Imitation Learning – Extended Version [article]

Timo P. Gros and Daniel Höller and Jörg Hoffmann and Verena Wolf
2020 arXiv   pre-print
We compare the performance of deep supervised learning, in particular imitation learning, to reinforcement learning for the Racetrack model.  ...  The resulting agents perform differently and their characteristics depend on those of the underlying learning approach.  ...  Racetrack is originally a pen and paper game, adopted as a benchmark in AI sequential decision making for the evaluation of MDP solution algorithms [2, 3, 13, 19] .  ... 
arXiv:2008.00766v1 fatcat:5raardybrrhphkf3mwqa6us3fq

Navier-Stokes flow simulation of the Space Shuttle Main Engine hot gas manifold

R.-J. YANG, J. L. C. CHANG, D. KWAK
1992 Journal of Spacecraft and Rockets  
Numerical solutions of the full equations become an alternative to understanding flowfields and provide insight necessary for components optimum de- sign.  ...  The number of mesh points in each zone are as follows: 103 x 52x 21 for the fuel bowl, 23 x 23 x45 for the transfer duct, and 41 x 53 x 21 for the racetrack, respectively.  ... 
doi:10.2514/3.26342 fatcat:x7eebihwmbesfoszcm2eypph34

Deep Statistical Model Checking [chapter]

Timo P. Gros, Holger Hermanns, Jörg Hoffmann, Michaela Klauck, Marcel Steinmetz
2020 Lecture Notes in Computer Science  
Neither is the verification technology available, nor is it even understood what a formal, meaningful, extensible, and scalable testbed might look like for such a technology.  ...  While being a straightforward extension of statistical model checking, it enables to gain deep insight into questions like "how high is the NN-induced safety risk?"  ...  This work was partially supported by ERC Advanced Investigators Grant 695614 (POWVER), and by DFG Grant 389792660 as part of TRR 248 (CPEC). The authors thank Felix Freiberger for technical support.  ... 
doi:10.1007/978-3-030-50086-3_6 fatcat:hqnjedbyendnbkmogkituzdjim

Apprenticeship learning with few examples

Abdeslam Boularias, Brahim Chaib-draa
2013 Neurocomputing  
To reduce this error, we introduce two new approaches for bootstrapping the demonstrations by assuming that the expert is near-optimal and the dynamics of the system is known.  ...  a linear combination of state and action features.  ...  of velocities, 5900 states for racetrack (1) , and 5100 states for racetrack (2) .  ... 
doi:10.1016/j.neucom.2012.11.002 fatcat:2wulbffwdrhgxlqj54pq5v6rsq

Autonomous Vehicles on the Edge: A Survey on Autonomous Vehicle Racing [article]

Johannes Betz, Hongrui Zheng, Alexander Liniger, Ugo Rosolia, Phillip Karle, Madhur Behl, Venkat Krovi, Rahul Mangharam
2022 arXiv   pre-print
We focus on the field of autonomous racecars only and display the algorithms, methods and approaches that are used in the fields of perception, planning and control as well as end-to-end learning.  ...  Researchers are developing software and hardware for high performance race vehicles which aim to operate autonomously on the edge of the vehicles limits: High speeds, high accelerations, low reaction times  ...  In addition, the teams provide insights in the middleware (e.g. ROS) as well as computations times of their algorithms.  ... 
arXiv:2202.07008v1 fatcat:hwhp43thevd2bighs7y7j7qnam

Temporal Memory with Magnetic Racetracks [article]

Hamed Vakili, Mohammad Nazmus Sakib, Samiran Ganguly, Mircea Stan, Matthew W. Daniels, Advait Madhavan, Mark D. Stiles, Avik W. Ghosh
2020 arXiv   pre-print
racetracks a natural memory for low-power, high-throughput race logic applications.  ...  Race logic is a relative timing code that represents information in a wavefront of digital edges on a set of wires in order to accelerate dynamic programming and machine learning algorithms.  ...  We would like to thank Andrew Kent, Joe Poon, Geoffrey Beach, and Brian Hoskins for insightful discussions.  ... 
arXiv:2005.10704v1 fatcat:oeeuwddncjfnhed7qyfr4cpa7e

Tilt mode stability scaling in field-reversed configurations with finite Larmor radius effect

Naotaka Iwasawa, Akio Ishida, Loren C. Steinhauer
2000 Physics of Plasmas  
MHD GROWTH RATE WITH TRUE EIGENVECTORS Recently, the algorithm for a Rayleigh-Ritz solution to the variational problem has been improved to allow a large basis set.  ...  Approximate but more insightful models have yielded similar results. 6 In short then, the FLR theory of static equilibria gave a reasonable explanation for the tilt stability of FRCs. II.  ...  This is true for both elliptic/hollow and racetrack/hollow equilibria.  ... 
doi:10.1063/1.873890 fatcat:xg42osh44nehlj3sv3maprk4uu

A FODO racetrack ring for nuSTORM: design and optimization

A. Liu, A. Bross, D. Neuffer
2017 Journal of Instrumentation  
In this paper, a FODO racetrack ring design and its optimization using sextupolar fields via both a Genetic Algorithm (GA) and a Simulated Annealing (SA) algorithm will be discussed.  ...  The goal of nuSTORM is to provide well-defined neutrino beams for precise measurements of neutrino cross-sections and oscillations.  ...  Mark Palmer for his supports on nuSTORM, Dr. David Adey for the discussions on the neutrino physics, and the MAP program colleagues on the discussions about the design.  ... 
doi:10.1088/1748-0221/12/07/p07018 fatcat:expbo36cxzfl3okzbzhwgvcxxi

Temporal Memory with Magnetic Racetracks

Hamed Vakili, Mohammad Nazmus Sakib, Samiran Ganguly, Mircea Stan, Matthew W. Daniels, Advait Madhavan, Mark D. Stiles, Avik W. Ghosh
2020 IEEE Journal on Exploratory Solid-State Computational Devices and Circuits  
make these magnetic racetracks a natural memory for low-power, high-throughput race logic applications.  ...  Race logic is a relative timing code that represents information in a wavefront of digital edges on a set of wires in order to accelerate dynamic programming and machine learning algorithms.  ...  ACKNOWLEDGMENT The authors would like to thank Andrew Kent, Joe Poon, Geoffrey Beach, Kai Litzius, and Brian Hoskins for insightful discussions.  ... 
doi:10.1109/jxcdc.2020.3022381 fatcat:n4wgq4wpovdnzgasyzxmahzhuq

ShiftsReduce: Minimizing Shifts in Racetrack Memory 4.0 [article]

Asif Ali Khan, Fazal Hameed, Robin Blaesing, Stuart Parkin, Jeronimo Castrillon
2019 arXiv   pre-print
We present an integer linear programming (ILP) formulation for optimal data placement in RMs, and revisit existing offset assignment heuristics, originally proposed for random-access memories.  ...  These operations are required to move bits to the right positions in the racetracks.  ...  We thank Andrés Goens for his useful input in the ILP formulation and Dr. Sven Mallach from Universität zu Köln (Cologne) for providing the sources of SOA heuristics.  ... 
arXiv:1903.03597v1 fatcat:3jbj7s5q65evpjnmgis7wfhc54

Surrogacy-Based Maximization of Output Power of a Low-Voltage Vibration Energy Harvesting Device

Marcin Kulik, Mariusz Jagieła, Marian Łukaniszyn
2020 Applied Sciences  
The results show very good performance of the strategy based on a sequentially refined kriging in terms of the ability to accurately localize extremum and reduction of the algorithm execution time.  ...  The purposeful optimization routine developed in this work is based on numerical identification of the turns that contribute most to the electromotive force and the elimination of those with the least  ...  (Figure 4a ) and for that with the optimized racetrack coils (Figure 4b ). As shown in Figure 5 , the output power increased as much as by 300%.  ... 
doi:10.3390/app10072484 fatcat:fsib6zxe2rewld4qej4ntlv4qu

Probabilistic Planning with Reduced Models

Luis Pineda, Shlomo Zilberstein
2019 The Journal of Artificial Intelligence Research  
The results place previous work on determinization in a broader context and lay the foundation for a systematic exploration of the space of model reductions.  ...  We show that each one of the dimensions---allowing more than one primary outcome or planning for some limited number of exceptions---could improve performance relative to standard determinization.  ...  Acknowledgments We thank Kyle Wray and Sandhya Saisubramanian for their helpful feedback and suggestions on earlier versions of this work.  ... 
doi:10.1613/jair.1.11569 fatcat:ththwrgymnb5bncdka3yr2txs4

Magnetic Racetrack Memory: From Physics to the Cusp of Applications Within a Decade

Robin Blasing, Asif Ali Khan, Panagiotis Ch. Filippou, Chirag Garg, Fazal Hameed, Jeronimo Castrillon, Stuart S. P. Parkin
2020 Proceedings of the IEEE  
ABSTRACT | Racetrack memory (RTM) is a novel spintronic memory-storage technology that has the potential to overcome fundamental constraints of existing memory and storage devices.  ...  This article shows how spin-orbitronics can successfully overcome impediments to technology transfer of racetrack memory, as FLASH and magnetic hard disk drives approach their fundamental physical limits  ...  To further reduce the shift overhead, the third heuristic applies a greedy algorithm for data allocation where the least frequently accessed data are stored on one end of the racetrack while the most frequently  ... 
doi:10.1109/jproc.2020.2975719 fatcat:usn4ypztv5drzid2y752qp46cm
« Previous Showing results 1 — 15 out of 739 results