arXiv subjects

Venkat Krovi

Publications and source records attributed to Venkat Krovi.

22 records · Page 2Linked to original sources

arXiv2022

A Failure Identification and Recovery Framework for a Planar Reconfigurable Cable Driven Parallel Robot

In cable driven parallel robots (CDPRs), a single cable malfunction usually induces complete failure of the entire robot. However, the lost static workspace (due to failure) can often be recovered through reconfiguration of the cable attachment points on the frame. This capability is introduced by adding kinematic redundancies to the robot in the form of moving linear sliders that are manipulated in a real-time redundancy resolution controller. The presented work combines this controller with an online failure detection framework to develop a complete fault tolerant control scheme for automatic task recovery. This solution provides robustness by combining pose estimation of the end-effector with the failure detection through the application of an Interactive Multiple Model (IMM) algorithm relying only on end-effector information. The failure and pose estimation scheme is then tied into the redundancy resolution approach to produce a seamless automatic task (trajectory) recovery approach for cable failures.

cs.RO↗

arXiv2022

Autonomous Vehicles on the Edge: A Survey on Autonomous Vehicle Racing

The rising popularity of self-driving cars has led to the emergence of a new research field in the recent years: Autonomous racing. 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, highly uncertain, dynamic and adversarial environments. This paper represents the first holistic survey that covers the research in the field of autonomous racing. 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. Further, with an increasing number of autonomous racing competitions, researchers now have access to a range of high performance platforms to test and evaluate their autonomy algorithms. This survey presents a comprehensive overview of the current autonomous racing platforms emphasizing both the software-hardware co-evolution to the current stage. Finally, based on additional discussion with leading researchers in the field we conclude with a summary of open research challenges that will guide future researchers in this field.

cs.RO↗

arXiv2021

Multi-level Knowledge Distillation via Knowledge Alignment and Correlation

Knowledge distillation (KD) has become an important technique for model compression and knowledge transfer. In this work, we first perform a comprehensive analysis of the knowledge transferred by different KD methods. We demonstrate that traditional KD methods, which minimize the KL divergence of softmax outputs between networks, are related to the knowledge alignment of an individual sample only. Meanwhile, recent contrastive learning-based KD methods mainly transfer relational knowledge between different samples, namely, knowledge correlation. While it is important to transfer the full knowledge from teacher to student, we introduce the Multi-level Knowledge Distillation (MLKD) by effectively considering both knowledge alignment and correlation. MLKD is task-agnostic and model-agnostic, and can easily transfer knowledge from supervised or self-supervised pretrained teachers. We show that MLKD can improve the reliability and transferability of learned representations. Experiments demonstrate that MLKD outperforms other state-of-the-art methods on a large number of experimental settings including different (a) pretraining strategies (b) network architectures (c) datasets (d) tasks.

cs.CV↗

arXiv2017

Matrix-Based Characterization of the Motion and Wrench Uncertainties in Robotic Manipulators

Characterization of the uncertainty in robotic manipulators is the focus of this paper. Based on the random matrix theory (RMT), we propose uncertainty characterization schemes in which the uncertainty is modeled at the macro (system) level. This is different from the traditional approaches that model the uncertainty in the parametric space of micro (state) level. We show that perturbing the system matrices rather than the state of the system provides unique advantages especially for robotic manipulators. First, it requires only limited statistical information that becomes effective when dealing with complex systems where detailed information on their variability is not available. Second, the RMT-based models are aware of the system state and configuration that are significant factors affecting the level of uncertainty in system behavior. In this study, in addition to the motion uncertainty analysis that was first proposed in our earlier work, we also develop an RMT-based model for the quantification of the static wrench uncertainty in multi-agent cooperative systems. This model is aimed to be an alternative to the elaborate parametric formulation when only rough bounds are available on the system parameters. We discuss that how RMT-based model becomes advantageous when the complexity of the system increases. We perform experimental studies on a KUKA youBot arm to demonstrate the superiority of the RMT-based motion uncertainty models. We show that how these models outperform the traditional models built upon Gaussianity assumption in capturing real-system uncertainty and providing accurate bounds on the state estimation errors. In addition, to experimentally support our wrench uncertainty quantification model, we study the behavior of a cooperative system of mobile robots. It is shown that one can rely on less demanding RMT-based formulation and yet meets the acceptable accuracy.

stat.AP↗