检索结果-内蒙古大学图书馆

FlashHack: Reflections on the Usage of a Micro Hackathon as an Assessment Tool in a Machine Learning Course

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Indra, R. Parthasarathy, P.D. Ambasana, Jatin Satavlekar, Spruha Department of Information Science and Engineering B.M.S. College of Engineering Bengaluru India Department of Computer Science and Information Systems BITS Pilani KK Birla Goa Campus Goa India Centre for Educational Technology Indian Institute of Technology Bombay Mumbai India

Machine learning (ML) course for undergraduates face challenges in assessing student learning and providing practical exposure. Group project-based learning, an increasingly popular form of experiential learning in CS education, encounters certain limitation in participation and non-participation from a few students. Studies also suggest that students find longer programming assignments and project-based assessments distracting and struggle to maintain focus when they coincide with other courses. To tackle these issues, we introduced FlashHack: a monitored, incremental, in-classroom micro Hackathon that combines project-based learning with Hackathon elements. Engaging 229 third year CS undergraduate students in teams of four, FlashHack prompted them to tackle predefined challenges using machine learning techniques within a set timeframe. Assessment criteria emphasized machine learning application, problem-solving, collaboration, and creativity. Our results indicate high student engagement and satisfaction, alongside simplified assessment processes for instructors. This experience report outlines the Hackathon design and implementation, highlights successes and areas for improvement making it feasible for replication by interested computing educators. © 2024, CC BY-NC-ND.

关键词： Adversarial machine learning

Haptic-based Complementary Filter for Rigid Body Rotations

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Kumar, Amit Campolo, Domenico Banavar, Ravi N. Centre for Systems and Control Indian Institute of Technology Bombay Mumbai India Singapore

The non-commutative nature of 3D rotations poses well-known challenges in generalizing planar problems to three-dimensional ones, even more so in contact-rich tasks where haptic information (i.e., forces/torques) is involved. In this sense, not all learning-based algorithms that are currently available generalize to 3D orientation estimation. Non-linear filters defined on SO(3) are widely used with inertial measurement sensors;however, none of them have been used with haptic measurements. This paper presents a unique complementary filtering framework that interprets the geometric shape of objects in the form of superquadrics, exploits the symmetry of SO(3), and uses force and vision sensors as measurements to provide an estimate of orientation. The framework’s robustness and almost global stability are substantiated by a set of experiments on a dual-arm robotic *** Codes 93C85 (Primary), 93B27 (Secondary) Copyright © 2025, The Authors. All rights reserved.

关键词： Geometry

Transient and asymptotic properties of robust adaptive controllers in the presence of non-coercive lyapunov functions

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Paranjape, Aditya A. Natarajan, Vivek Ghosh, Supratim Tcs Research India Systems and Control Engineering Group Indian Institute of Technology Bombay Mumbai India

Adaptive control architectures often make use of Lyapunov functions to design adaptive laws. We are specifically interested in adaptive control methods, such as the well-known L1 adaptive architecture, which employ a parameter observer for this purpose. In such architectures, the observation error plays a critical role in determining analytical bounds on the tracking error as well as robustness. In this paper, we show how the non-existence of coercive Lyapunov operators can impact the analytical bounds, and with it the performance and the robustness of such adaptive *** Codes 93C20, 93C25, 93C40, 93D05 Copyright © 2021, The Authors. All rights reserved.

关键词： Lyapunov functions

Constructing Dynamic Feedback Linearizable Discretizations.

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Jindal, Ashutosh Nicolau, Florentina Diego, David Martín Banavar, Ravi Systems and Control Engineering Indian Institute of Technology Bombay Maharashtra Mumbai400076 India Quartz EA7393 École Nationale Supérieure de l’Électronique et de ses Applications Cergy France Calle Nicolás Cabrera 13-15 Madrid28049 Spain

Dynamic feedback linearization-based methods allow us to design control algorithms for a fairly large class of nonlinear systems in continuous time. However, this feature does not extend to their sampled counterparts, i.e., for a given dynamically feedback linearizable continuous time system, its numerical discretization may fail to be so. In this article, we present a way to construct discretization schemes (accurate up to first order) that result in schemes that are feedback linearizable. This result is an extension of our previous work, where we had considered only static feedback linearizable systems. The result presented here applies to a fairly general class of nonlinear systems, in particular, our analysis applies to both endogenous and exogenous types of feedback. While the results in this article are presented on a control affine form of nonlinear systems, they can be readily modified to general nonlinear systems. © 2024, CC BY.

关键词： Nonlinear systems

Time-Constrained Individual Homing Guidance against Stationary Targets

学校读者我要写书评

暂无评论

Time-Constrained Individual Homing Guidance against Stationa...

control Conference (ICC), 2019 Sixth indian

作者： Rohit Nanavati Shashi Ranjan Kumar Arnab Maity Intelligent Systems & Control Laboratory Indian Institute of Technology Bombay Powai India

ISBN: (纸本)9781665409797

In this paper, terminal sliding mode control based impact time-constrained guidance strategies are proposed, which enable the pursuers to achieve individual homing based simultaneous interception of a stationary target. Guidance commands are derived using switching surfaces based on range errors and their rates. As the guidance laws are designed using nonlinear engagement kinematics, the proposed strategies achieve salvo interception at desired impact time even for the engagement with large heading angle errors. Unlike most of the existing guidance strategies, the proposed guidance strategies circumvent the possible degradations due to erroneous time-to-go estimates. The proposed strategies are shown to perform satisfactorily for different impact times and also exhibited desirable terminal features as compared to existing salvo strategies.

关键词： Degradation Switches Kinematics Numerical simulation Surface treatment Sliding mode control Convergence

Impact Angle Constrained Integrated Guidance and control for a Dual-controlled Interceptor

学校读者我要写书评

暂无评论

Impact Angle Constrained Integrated Guidance and Control for...

control Conference (ICC), 2019 Sixth indian

作者： Abhinav Sinha Rohit V. Nanavati Shashi Ranjan Kumar Intelligent Systems & Control Lab Indian Institute of Technology Bombay Mumbai India

ISBN: (纸本)9781665409797

In this work, we address the problem of an angle-constrained interception within an integrated guidance and control framework. We consider a dual-controlled interceptor (an interceptor equipped with canard and tail aerodynamic control surfaces), and design fin deflection commands directly to effect the lateral acceleration needed to steer the interceptor on a course leading to interception of a stationary target with constrained impact angle. We use a weighted effort allocation scheme that apportions the available effort in canard and tail surfaces to generate the required lateral acceleration. With an additional degree of freedom, our design exhibits fault-tolerance and is also capable to address other objectives. We present the overall design using sliding mode control to make the design insensitive to modeling errors and parametric uncertainties. We, further, demonstrate the efficacy of our design via numerical simulations.

关键词： Fault tolerance Uncertainty control design Fault tolerant systems Aerodynamics Numerical simulation Numerical models

Cooperative Target Capture Using Predefined-Time Consensus

学校读者我要写书评

暂无评论

Cooperative Target Capture Using Predefined-Time Consensus

control Conference (ICC), 2019 Sixth indian

作者： Abhinav Sinha Shashi Ranjan Kumar Intelligent Systems & Control Lab Indian Institute of Technology Bombay Mumbai India

ISBN: (纸本)9781665409797

This paper presents predefined-time consensus-based cooperative guidance laws for a swarm of interceptors to simultaneously capture a non-maneuvering target. Unlike leader-follower cooperative guidance techniques, we design laws for a swarm of interceptors that has no leader and each interceptor executes its own distributed cooperative guidance command. This obviates the residency of the mission over a single interceptor. First, we present the cooperative guidance command against a stationary target, and extend the proposed design using two different approaches for simultaneous interception of a target moving with constant speed. Rigorously, we show that the proposed cooperative guidance laws guarantee consensus in the interceptors’ time-to-go values within a predefined-time. The proposed design allows a feasible time of consensus in time-to-go to be set arbitrarily at will during the design regardless of the interceptors’ initial time-to-go values, thereby ensuring a simultaneous interception in various engagement scenarios. We also demonstrate the efficacy of the proposed design via simulations.

关键词： Dynamics Switches control systems

Surgical Proficiency Assessment Using Virtual Reality (Vr)-Based Hybrid Simulation for Minimally Invasive Procedures

学校读者我要写书评

暂无评论

SSRN

SSRN 2025年

作者： Jain, Saurabh Lee, Seunghan Barber, Samuel Ralph Son, Young-Jun Department of Industrial Engineering and Operations Research Indian Institute of Technology Bombay Mumbai India Department of Industrial Engineering and Systems Engineering Mississippi State University Starkville United States Department of ENT & Skull Base Surgery Barrow Neurological Institute Phoenix United States Edwardson School of Industrial Engineering Purdue University West Lafayette United States

Technological advances in extended reality (XR: technology incorporating virtual reality (VR), augmented reality (AR), and mixed reality (MR)) have spurred the development of surgical simulators with the goal of immersing the user in the environment. However, there has been only incremental progress in developing surgical proficiency assessments that are critical in utilizing this technology to train safer and more efficient surgeons. We hypothesize that baseline measurements of expert surgeons (ground truth) and comparisons between users of different proficiency levels can be analyzed to develop an accurate proficiency classification of trainees on a VR-surgical simulator. The foundation of this work is based on our functional endoscopic sinus simulator (FESS) which incorporates a hierarchical task-based analysis of sinus surgery with motion-tracking of the endoscope and surgical instruments. We utilized dynamic time warping (DTW) to combine motion-tracking and operative time of sinus surgery experts to estimate a ground truth, developed a classification network combining motion-tracking and operative time using Decision Tree C5.0, and validated the accuracy of the proficiency classification by conducting extensive experiments with novice (n=28) and expert (n=24) users. The proposed work is critical to provide personalized and directed feedback to efficiently train surgeons utilizing simulation. © 2025, The Authors. All rights reserved.

关键词： Motion tracking

An Inexact Frank-Wolfe Algorithm for Composite Convex Optimization Involving a Self-Concordant Function

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Shinde, Nimita Narayanan, Vishnu Saunderson, James Department of Industrial and Systems Engineering Lehigh University BethlehemPA18015 United States Industrial Engineering and Operations Research Indian Institute of Technology Bombay Powai Mumbai400076 India Department of Electrical and Computer Systems Engineering Monash University ClaytonVIC3800 Australia

In this paper, we consider Frank-Wolfe-based algorithms for composite convex optimization problems with objective involving a logarithmically-homogeneous, self-concordant functions. Recent Frank-Wolfe-based methods for this class of problems assume an oracle that returns exact solutions of a linearized subproblem. We relax this assumption and propose a variant of the Frank-Wolfe method with inexact oracle for this class of problems. We show that our inexact variant enjoys similar convergence guarantees to the exact case, while allowing considerably more flexibility in approximately solving the linearized subproblem. In particular, our approach can be applied if the subproblem can be solved prespecified additive error or to prespecified relative error (even though the optimal value of the subproblem may not be uniformly bounded). Furthermore, our approach can also handle the situation where the subproblem is solved via a randomized algorithm that fails with positive probability. Our inexact oracle model is motivated by certain large-scale semidefinite programs where the subproblem reduces to computing an extreme eigenvalue-eigenvector pair, and we demonstrate the practical performance of our algorithm with numerical experiments on problems of this form. © 2023, CC BY.

关键词： Eigenvalues and eigenfunctions