SLAMBooster: An Application-Aware Online Controller for Approximation in Dense SLAM

Simultaneous Localization and Mapping (SLAM) is the problem of constructing a map of a mobile agent's environment while localizing the agent within the map. Dense SLAM algorithms perform reconstruction and localization at pixel granularity. These algorithms require a lot of computational power, which has hindered their use on low-power resource-constrained devices. Approximate computing can be used to speed up SLAM implementations as long as the approximations do not prevent the agent from navigating correctly through the environment. Previous studies of approximation in SLAM have assumed that the entire trajectory of the agent is known before the agent starts, and they have focused on offline controllers that set approximation knobs at the start of the trajectory. In practice, the trajectory is usually not known ahead of time, and allowing knob settings to change dynamically opens up more opportunities for reducing computation time and energy. In this paper, we describe SLAMBooster, an application-aware, online control system for dense SLAM that adaptively controls approximation knobs during the motion of the agent. SLAMBooster is based on a control technique called proportional-integral-derivative (PID) controller but our experiments showed this application-agnostic controller led to an unacceptable reduction in localization accuracy. To address this problem, SLAMBooster also exploits domain knowledge for controlling approximation by performing smooth surface detection and pose correction. We implemented SLAMBooster in the open-source SLAMBench framework and evaluated it on more than a dozen trajectories from both the literature and our own study. Our experiments show that on the average, SLAMBooster reduces the computation time by 72% and energy consumption by 35% on an embedded platform, while maintaining the accuracy of localization within reasonable bounds. These improvements make it feasible to deploy SLAM on a wider range of devices.

[1]  Mohinder S. Grewal,et al.  Kalman Filtering: Theory and Practice , 1993 .

[2]  Kailash Gopalakrishnan,et al.  Energy-Efficient Simultaneous Localization and Mapping via Compounded Approximate Computing , 2016, 2016 IEEE International Workshop on Signal Processing Systems (SiPS).

[3]  Paul H. J. Kelly,et al.  Algorithmic Performance-Accuracy Trade-off in 3D Vision Applications Using HyperMapper , 2017, 2017 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW).

[4]  Xin Zhang,et al.  FlexJava: language support for safe and modular approximate programming , 2015, ESEC/SIGSOFT FSE.

[5]  Henry Hoffmann,et al.  CALOREE: Learning Control for Predictable Latency and Low Energy , 2018, ASPLOS.

[6]  Olivier Stasse,et al.  MonoSLAM: Real-Time Single Camera SLAM , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Amin Ansari,et al.  Using Multiple Input, Multiple Output Formal Control to Maximize Resource Efficiency in Architectures , 2016, 2016 ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA).

[8]  Woongki Baek,et al.  Green: a framework for supporting energy-conscious programming using controlled approximation , 2010, PLDI '10.

[9]  Martin C. Rinard,et al.  Verifying quantitative reliability for programs that execute on unreliable hardware , 2013, OOPSLA.

[10]  Andrew J. Davison,et al.  A benchmark for RGB-D visual odometry, 3D reconstruction and SLAM , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[11]  Christos-Savvas Bouganis,et al.  Semi-dense SLAM on an FPGA SoC , 2016, 2016 26th International Conference on Field Programmable Logic and Applications (FPL).

[12]  Swarnendu Biswas,et al.  An elementary introduction to Kalman filtering , 2017, Commun. ACM.

[13]  Michael F. P. O'Boyle,et al.  Introducing SLAMBench, a performance and accuracy benchmarking methodology for SLAM , 2014, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[14]  Scott A. Mahlke,et al.  Rumba: An online quality management system for approximate computing , 2015, 2015 ACM/IEEE 42nd Annual International Symposium on Computer Architecture (ISCA).

[15]  John J. Leonard,et al.  Kintinuous: Spatially Extended KinectFusion , 2012, AAAI 2012.

[16]  Scott A. Mahlke,et al.  Paraprox: pattern-based approximation for data parallel applications , 2014, ASPLOS.

[17]  Henry Hoffmann,et al.  JouleGuard: energy guarantees for approximate applications , 2015, SOSP.

[18]  Henry Hoffmann,et al.  POET: a portable approach to minimizing energy under soft real-time constraints , 2015, 21st IEEE Real-Time and Embedded Technology and Applications Symposium.

[19]  Davide Scaramuzza,et al.  SVO: Fast semi-direct monocular visual odometry , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[20]  Hugh F. Durrant-Whyte,et al.  Simultaneous localisation and map building for autonomous guided vehicles , 1994, Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'94).

[21]  Michael F. P. O'Boyle,et al.  Integrating algorithmic parameters into benchmarking and design space exploration in 3D scene understanding , 2016, 2016 International Conference on Parallel Architecture and Compilation Techniques (PACT).

[22]  James J. Little,et al.  Vision-based SLAM using the Rao-Blackwellised Particle Filter , 2005 .

[23]  J. M. M. Montiel,et al.  ORB-SLAM: A Versatile and Accurate Monocular SLAM System , 2015, IEEE Transactions on Robotics.

[24]  G. Klein,et al.  Parallel Tracking and Mapping for Small AR Workspaces , 2007, 2007 6th IEEE and ACM International Symposium on Mixed and Augmented Reality.

[25]  Andrew W. Fitzgibbon,et al.  KinectFusion: Real-time dense surface mapping and tracking , 2011, 2011 10th IEEE International Symposium on Mixed and Augmented Reality.

[26]  Henry Hoffmann,et al.  MEANTIME: Achieving Both Minimal Energy and Timeliness with Approximate Computing , 2016, USENIX Annual Technical Conference.

[27]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[28]  Paul H. J. Kelly,et al.  Application-oriented design space exploration for SLAM algorithms , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[29]  John J. Leonard,et al.  Real-time large-scale dense RGB-D SLAM with volumetric fusion , 2014, Int. J. Robotics Res..

[30]  Keshav Pingali,et al.  Proactive Control of Approximate Programs , 2016, ASPLOS.

[31]  Olaf Kähler,et al.  Very High Frame Rate Volumetric Integration of Depth Images on Mobile Devices , 2015, IEEE Transactions on Visualization and Computer Graphics.

[32]  Andrew W. Fitzgibbon,et al.  KinectFusion: real-time 3D reconstruction and interaction using a moving depth camera , 2011, UIST.

[33]  Claude Sammut,et al.  GPU accelerated graph SLAM and occupancy voxel based ICP for encoder-free mobile robots , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[34]  Henry Hoffmann,et al.  Automated design of self-adaptive software with control-theoretical formal guarantees , 2014, Software Engineering & Management.

[35]  Michael Bosse,et al.  Keyframe-based visual–inertial odometry using nonlinear optimization , 2015, Int. J. Robotics Res..

[36]  Dan Grossman,et al.  Expressing and verifying probabilistic assertions , 2014, PLDI.

[37]  Dan Grossman,et al.  EnerJ: approximate data types for safe and general low-power computation , 2011, PLDI '11.

[38]  Daniel Cremers,et al.  LSD-SLAM: Large-Scale Direct Monocular SLAM , 2014, ECCV.

[39]  Stefan Leutenegger,et al.  ElasticFusion: Dense SLAM Without A Pose Graph , 2015, Robotics: Science and Systems.

[40]  Martin C. Rinard,et al.  Proving acceptability properties of relaxed nondeterministic approximate programs , 2012, PLDI.

[41]  Federico Tombari,et al.  CNN-SLAM: Real-Time Dense Monocular SLAM with Learned Depth Prediction , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[42]  Mohinder S. Grewal,et al.  Kalman Filtering: Theory and Practice Using MATLAB , 2001 .

[43]  Henry Hoffmann,et al.  Managing performance vs. accuracy trade-offs with loop perforation , 2011, ESEC/FSE '11.

[44]  Norman S. Nise,et al.  Control Systems Engineering , 1991 .