Browsing by Author "Gautam, Avinash"

Now showing 1 - 20 of 31

Autonomous Mapping and Navigation using Fiducial Markers and Pan-Tilt Camera for Assisting Indoor Mobility of Blind and Visually Impaired People
(2023-10) Gautam, Avinash; Shekhawat, Virendra Singh; Mohan, Sudeept
Large indoor spaces have complex layouts making them difficult to navigate. Indoor spaces in hospitals, universities, shopping complexes, etc., carry multi-modal information in the form of text and symbols. Hence, it is difficult for Blind and Visually Impaired (BVI) people to independently navigate such spaces. Indoor environments are usually GPS-denied; therefore, Bluetooth-based, WiFi-based, or Range-based methods are used for localization. These methods have high setup costs, lesser accuracy, and sometimes need special sensing equipment. We propose a Visual Assist (VA) system for the indoor navigation of BVI individuals using visual Fiducial markers for localization. State-of-the-art (SOTA) approaches for visual localization using Fiducial markers use fixed cameras having a narrow field of view. These approaches stop tracking the markers when they are out of sight. We employ a Pan-Tilt turret-mounted camera which enhances the field of view to 360° for enhanced marker tracking. We, therefore, need fewer markers for mapping and navigation. The efficacy of the proposed VA system is measured on three metrics, i.e., RMSE (Root Mean Square Error), ADNN (Average Distance to Nearest Neighbours), and ATE (Absolute Trajectory Error). Our system outperforms Hector-SLAM, ORB-SLAM3, and UcoSLAM. The proposed system achieves localization accuracy within ±8cm compared to ±12cm and ±10cm for ORB-SLAM3 and UcoSLAM, respectively.
Balanced partitioning of workspace for efficient multi-robot coordination
(IEEE, 2017) Shekhawat, Virendra Singh; Gautam, Avinash; Mohan, Sudeept
Multi-robot terrain coverage approaches that are based on Voronoi partitioning produce unbalanced partitions of the workspace resulting in uneven distribution of the workload to the individual robots. The proposed approach creates partitions of the workspace such that the regions to be covered by individual robots are maximally balanced. This type of partitioning can be especially useful in tasks like floor cleaning, surveillance etc. The proposed approach is suitable for use in indoor environments like office buildings, hospitals etc. It is assumed that the grid map of the workspace is already known. The workspace is transformed into a topological weighted connected graph. Vertex weight is defined by the size of the area it represents. This graph is then partitioned into sub-graphs that are maximally balanced in terms of vertex weights using genetic algorithm. These sub-graphs thus obtained represent balanced partitions which are assigned to the individual robots for further processing.
CF-HMRTA: coalition formation for heterogeneous multi-robot task allocation
(Springer, 2025-07) Gautam, Avinash; Shekhawat, Virendra Singh; Mohan, Sudeept
This paper introduces a novel approach, Coalition Formation for Heterogeneous Multi-Robot Task Allocation (CF-HMRTA), to address the challenge of multi-robot task allocation. The problem, inherently NP-Hard, is tackled using bipartite graph matching. CF-HMRTA forms heterogeneous robot coalitions with unique service skills to complete tasks collaboratively, using a heuristic algorithm for optimal robot-task pairing while preventing task overlap. Recent research work using bipartite graph matching for multi-robot coalition formation and task allocation often assumes homogeneity across tasks and robots, where any robot can be assigned to any task. In contrast, the solution proposed in this paper explicitly considers the diversity of robots with varying service skills. Additionally, tasks demand different sets of skills, such as sensing, monitoring, and data collection, making certain tasks unsuitable for some robots due to hardware constraints. For instance, tasks requiring aerial footage are assigned to drones, while ground robots handle close-ground monitoring. Furthermore, we incorporate task-specific time constraints into our problem formulation, enhancing its realism. Considerably less research has been conducted on heterogeneous robot teams solving tasks that require multiple service skills and temporal constraints, making our work a significant contribution to the field. The algorithm achieves a worst-case time complexity of , where represents the edges in the bipartite graph, and guarantees perfect matching. Simulation results highlight its scalability, successfully allocating up to 2000 robots to 400 tasks in approximately 11 seconds.
Cluster, Allocate, Cover: An Efficient Approach for Multi-robot Coverage
(IEEE, 2015) Mohan, Sudeept; Gautam, Avinash
This article presents an algorithm for online multirobot coverage that proceeds with minimal knowledge of the already explored region and the frontier cells. It creates clusters of frontier cells which are designated to robots using an optimal assignment scheme. Coverage is then performed using a novel path planning technique. Many approaches that use clustering for multi-robot coverage do not specify strict time criteria for re-clustering. Moreover, the motion plans they use result in redundant coverage. To overcome these limitations, an appropriate motion plan for the robots is chosen based on the context of already covered frontiers. Dispersion of robots is vital for efficient coverage and is an emergent behavior in our approach. The efficacy of the proposed approach is tested in simulation and on a multi-robot test-bed. The algorithm performs better than some state of the art approaches.
COMPOSV++: Light Weight Online Signature Verification Framework Through Compound Feature Extraction and Few-Shot Learning
(ACM Digital Library, 2022) Gautam, Avinash
Online Signature Verification (OSV) is a systematically used biometric characteristic to endorse the genuineness of a user to access real time applications like healthcare, m-payment, etc. Because OSV frameworks are used in real-time applications and it is difficult to acquire a sufficient number of signature samples from users, they must meet a critical requirement: they must be able to detect skilled and random signature presentation attacks effectively with fewer training signature samples and a faster response time. To meet these needs, we developed a depth wise separable (DWS) convolution-based OSV framework that realizes one/few shot learning in inference phase. In addition to it, we have designed a compound feature extraction technique, which extracts maximum seven features from a set of 100 features in MCYT-100, and 3 features from a set of 47 in case of {SVC, SUSIG} datasets. The framework uses only three to seven features per signature to resist the signature presentation attacks. We have extensively evaluated our framework, by performing thorough experiments with three datasets i.e. MCYT-100, SVC and SUSIG. The model results state of the art EER in all skilled categories of SVC and SUSIG datasets.
COMPOSV: compound feature extraction and depthwise separable convolution-based online signature verification
(Springer, 2022-02) Gautam, Avinash
Online signature verification (OSV) is a predominantly used verification framework, which is intended to authenticate the legitimacy of a test signature by learning the writer specific signing characteristics. The significant adoption of OSV in critical applications like E-Commerce, M-Payments, etc., emphasizes on a framework which addresses critical requirements: (1) The framework should be competent to classify a test signature with few training samples, as minimum as one per user and with the least number of features extracted per signature, and (2) The framework should accurately classify a test signature of an unseen user. Even though several OSV frameworks are proposed based on various advanced techniques, still there is a necessity for a holistic OSV framework which is able to accomplish the abovementioned requirement criteria. To realize the above requirements, we present a depthwise separable (DWS) convolution-based OSV framework which facilitate the classification of test signature samples from an unseen user. In addition to this, we introduce a novel dimensionality reduction-based feature extraction technique, which decrease the dimensionality of a set of features from 100 to 3 concerning to MCYT-330, MCYT-100 and 47 to 3 with regard to SVC, SUSIG datasets. To appraise the competence of our proposed COMPOSV framework, extensive experiments and ablation studies are conducted on four widely used datasets, i.e., MCYT-100, MCYT-330, SVC and SUSIG. The proposed framework, trained with signature samples of only 10% of users (seen), can classify the signatures of 90% of unseen users with higher accuracy than the frameworks trained with signature samples of all users.
D-MRFTE: A Decentralized Relay-Based Approach for Multi-Robot Unknown Area Exploration
(IEEE, 2023) Gautam, Avinash; Mohan, Sudeept; Shekhawat, Virendra Singh
In this paper, a decentralized relay-based approach (D-MRFTE) for unknown area exploration using a team of autonomous mobile robots is proposed under communication constraints. Using the relay robots, the multi-robot system forms a high-latency decentralized network with distributed copies of exploration information for which eventual consistency and completeness are ensured through meetups. The meetups act as a safety net and set a bound on latency by ensuring data transfer at periodic intervals whenever the multi-robot network gets fragmented. The information exchange related to the robot’s state and the ongoing exploration is facilitated by the relay robots. The robots use timestamps to assimilate the latest available information by using version vectors. To achieve a consistent state of explorer robots, the relays schedule meetups with other relays they come in contact with, creating a tightly-knit group. Our approach, under two communication models, i.e., Disk-based and Line-of-Sight-based, exhibits superior performance compared with two state-of-the-art algorithms in terms of completion time and distance traveled by the robot team. The simulations are conducted in a Player/Stage simulator with different robot team sizes.
Datacenter Workload Classification and Characterization: An Empirical Approach
(IEEE, 2018) Shekhawat, Virendra Singh; Gautam, Avinash
Datacenter traffic has increased significantly due to rising number of web applications on Internet. These applications have diverse Quality of Service (QoS) requirements making datacenter management a complex task. For a datacenter the amount of resources required for a given resource type (computing, memory, network and storage) is termed as workload. In cloud datacenters, workload classification and characterization is used for resource management, application performance management, capacity sizing, and for estimating the future resource demand. An accurate estimation of future resource demand helps in meeting QoS requirements and ensure efficient resource utilization. Thus modeling and characterization of datacenter workloads becomes necessary to meet performance requirements of applications in a cost-efficient manner. In this paper, a methodology to classify datacenter workloads and characterize them based on resource usage is proposed. Two different workloads have been used, one is Google Cluster Trace (GCT) dataset and other is Bit Brains Trace (BBT) dataset. Seven different machine learning algorithms for workload classification have been used. Workload distribution is estimated in a mix of heterogeneous applications for both GCT and BBT. The seven machine learning algorithms have been compared on the basis of their classification accuracy. Finally, an algorithm to estimate the importance of different attributes for classification is proposed in this paper.
De-COP: A Decentralized Community Convergence Approach for Message Forwarding in Pocket Switched Networks
(IEEE, 2022) Shekhawat, Virendra Singh; Gautam, Avinash
Pocket Switched Networks (PSNs) are an evolution of mobile ad-hoc and Delay Tolerant Networks in which there is no assumption made about the existence of a complete path between two nodes wishing to communicate, thus making routing even more challenging. Various routing algorithms have been proposed over the years like Epidemic, Spray and Wait, ProPHET, etc. There is a separate class of routing algorithms that exploit social structuralism to selectively forward messages to the best candidates. One such algorithm is BUBBLE Rap, which takes into account the notion of popularity and communities to make forwarding decisions. However, popularity as a sole deal-breaker is a rigid policy. We propose a decentralized community convergence-based message forwarding approach viz., De-COP that makes use of the familiarity metric which is dictated by the characteristic of a community to make message forwarding decisions. When familiarity is used for forwarding messages in converged communities, the messages are delivered with low latency and high probability. A community is defined as converged when the change in its membership is gradual. The forwarding node also takes into account the butter availability at the target node to reduce delay and message loss probability. The results were obtained using ONE simulator on two popular datasets, i.e., Infocomm06 and Cambridge to demonstrate the efficacy of the proposed De-COP approach in terms of improved delivery probability and message overhead ratio compared to ProPHET and BUBBLE Rap.
Design and Implementation of Efficient Coordination Algorithms for Multi Robot Systems
(BITS, Pilani, 2016-08) Gautam, Avinash
A distributed algorithm for balanced multi-robot task allocation
(IEEE, 2016) Gautam, Avinash; Mohan, Sudeept
In this paper the problem of static multi-robot task allocation is addressed. It is concerned with the distribution of static tasks in an environment to robots such that the robots complete the tasks in an optimal fashion. The cost of completing a task is proportional to the distance travelled by a robot to visit that task. This problem is of particular importance in multi-robot systems because finding an optimal solution is NP-hard. Earlier work has paid less attention towards load balanced task allocation. In this paper, a completely distributed algorithm is proposed. A travelling salesman tour (TST) considering all task locations is computed using distributed genetic algorithm. The TST is partitioned into fragments that are distributed amongst the robots using a novel auction algorithm. The proposed algorithm is compared with a state of the art algorithm in simulation. The results thus obtained substantiate the fact that the proposed algorithm shows improved performance in terms of load balanced distribution of tasks to the individual robots in multi-robot system.
A distributed algorithm for circle formation by multiple mobile robots
(IEEE, 2013) Gautam, Avinash; Mohan, Sudeept
This paper suggests a distributed, decentralized approach for positioning multiple mobile robots in a circular formation in a semi synchronous setting. The problem of the circle formation with multiple robots which are arbitrarily placed on a 2D plane requires all robots to be uniformly positioned (i.e., at an equal angular distance of 2ŏ/N, where N = number of robots) on the circle circumference. The suggested approach uses explicit inter robot communication by way of message passing and forms a token ring based network. It uses the distributed solution of one of the classical synchronization problem often used in distributed systems, the Dining Philosopher Problem, for the robots to synchronize during their activation cycles.
DTA-HMR-TT: dynamic task allocation for a heterogeneous team of mobile robots with task transfer
(IEEE, 2024-11) Gautam, Avinash; Shekhawat, Virendra Singh; Mohan, Sudeept
Managing time-sensitive deliveries in settings like hospitals is a challenging task, especially when multiple pickup and delivery requests need to be coordinated efficiently within strict time windows. This paper focuses on the Multi-Pickup and Delivery Problem with Time Windows (MPDPTW), where a fleet of autonomous mobile robots works together to fulfill client requests that involve picking up items from specified origins and delivering them to designated destinations. Our objective is to minimize penalties associated with late deliveries while maximizing the number of successfully completed requests. To address this, we introduce a novel approach using a heterogeneous team of robots equipped with an efficient and cost-effective scheduling algorithm. Users submit requests with specific time constraints, and our proposed decentralized algorithm-Dynamic Task Allocation for Heterogeneous Mobile Robots with Task Transfer (DTA-HMR-TT)–optimizes task sharing between robots, ensuring timely service. The algorithm dynamically adjusts to handle rejected or delayed tasks and manages the complex transfer of tasks between robots to improve delivery efficiency. Extensive simulations have demonstrated that our approach significantly outperforms state-of-the-art methods. For smaller task sets (50 to 150 tasks), penalties were reduced by 27%, while for larger sets (150 to 300 tasks), penalties were lowered by 36%. Our results highlight the effectiveness of DTA-HMR-TT in enhancing task scheduling and coordination in multi-robot systems, offering a promising solution for improving delivery performance in structured environments.
Efficient content caching for named data network nodes
(ACM Digital Library, 2020-02) Shekhawat, Virendra Singh; Gautam, Avinash
Named Data Networking (NDN) is a promising Content-Centric Network (CCN) architecture that supports data distribution and data sharing by in-network ubiquitous content caching. In NDN, each router has content store to cache data packets passed by and, therefore, frequently requested content by consumers (e.g., end hosts) is cached at multiple routers in the network. Content caching at routers enables data delivery to consumers from a nearest location with minimal latency and thereby enhances overall network performance. Content store at nodes should have sufficient space to hold the current frame of locality of reference for attaining a good hit rate. The content store size requirement for each node is different due to their topological characteristics. Homogeneous caching mechanisms distribute the total cache budget equally among the nodes irrespective of their topological characteristics. In contrast, heterogeneous caching allocates cache to the nodes based on their topological importance. In this paper, a heterogeneous on-path cache budget distribution approach is proposed that distributes cache to the content stores based on reference locality of the nodes. The proposed cache distribution algorithm is evaluated for structured and unstructured network topology using the ndnSIM simulator. The results are compared with the homogeneous cache distribution mechanism and 14% improvement in cache hit rate is achieved.
Experimental Evaluation of Multi-Robot Online Terrain Coverage Approach
(IEEE, 2018) Shekhawat, Virendra Singh; Gautam, Avinash; Mohan, Sudeept
This paper presents a empirical evaluation of some approaches suggested in the literature for solving the online terrain coverage task. Our first contribution is that, we have implemented in simulation four state-of-the-art approaches. The first two approaches are based on structured trajectories and use backtracking mechanism for task allocation. The other two are based on the behavior of ants. Also, we have modified one of the state-of-the-art approaches and improved its performance in terms of computation time. The second contribution is that, we have developed a practical test-bed comprising of multiple differential drive robots that are able to coordinate with each other in a distributed fashion by wirelessly communicating with their team-mates. We have implemented the representative set of approaches on our test-bed. The same test-bed can be leveraged for validating multi-robot coordination approaches for solving other tasks like patrolling, foraging, etc.
FAST Synchronous Frontier Allocation for Scalable Online Multi-Robot Terrain Coverage
(Springer, 2016-09) Mohan, Sudeept; Gautam, Avinash
We propose Frontier Allocation Synchronized by Token passing (FAST), a distributed algorithm for online terrain coverage using multiple mobile robots, ensuring mutually exclusive selection of frontier cells. Many existing approaches cover the terrain in an irregular fashion, without considering the usability of the already covered region. For instance, in the task of floor cleaning in an office building, these approaches do not guarantee the cleanliness of large unbroken areas until a majority of the task is complete. FAST on the other hand, incrementally traverses the terrain generating structured trajectories for each robot. Following a structured trajectory for coverage path planning is proven to be a very powerful approach in literature. This renders large portions of the terrain usable even before the completion of the coverage task. The novel map representation techniques used in FAST render it scalable to large terrains, without affecting the volume of communication among robots. Moreover, the distributed nature of FAST allows incorporation of fault-tolerance mechanisms.
FAST: Synchronous Frontier Allocation for Scalable Online Multi-Robot Terrain Coverage
(Springer, 2017-09) Gautam, Avinash; Mohan, Sudeept
We propose Frontier Allocation Synchronized by Token passing (FAST), a distributed algorithm for online terrain coverage using multiple mobile robots, ensuring mutually exclusive selection of frontier cells. Many existing approaches cover the terrain in an irregular fashion, without considering the usability of the already covered region. For instance, in the task of floor cleaning in an office building, these approaches do not guarantee the cleanliness of large unbroken areas until a majority of the task is complete. FAST on the other hand, incrementally traverses the terrain generating structured trajectories for each robot. Following a structured trajectory for coverage path planning is proven to be a very powerful approach in literature. This renders large portions of the terrain usable even before the completion of the coverage task. The novel map representation techniques used in FAST render it scalable to large terrains, without affecting the volume of communication among robots. Moreover, the distributed nature of FAST allows incorporation of fault-tolerance mechanisms.
A Graph Partitioning Approach for Fast Exploration with Multi-Robot Coordination
(IEEE, 2019) Shekhawat, Virendra Singh; Mohan, Sudeept; Gautam, Avinash
A multi-robot exploration approach is suggested in this paper that works on the premise that the topo-metric map of the indoor environment is known a priori. Genetic Algorithms (GAs) are used for spatial partitioning of the topo-metric graph of the environment. Each spatial partition, which represents the sub-graph, is apportioned to a unique robot by using the Hungarian method for task assignment in conjunction with Bully Algorithm for leader election. In the case of robot(s) failure, graph re-partitioning and single item auctions are used for re-assigning the remaining task(s) of the failed robot(s) to other robots. The proposed approach performs better than a recent state-of-the-art strategy that employs Delaunay triangulation and multi-prim algorithm for multi-robot exploration. Empirical results obtained in simulation by varying the number of robots in two different and complex environments prove the efficacy of the proposed approach.
HMR-ODTA: online diverse task allocation for a team of heterogeneous mobile robots
(2025-05) Gautam, Avinash; Shekhawat, Virendra Singh; Mohan, Sudeept
Coordinating time-sensitive deliveries in environments like hospitals poses a complex challenge, particularly when managing multiple online pickup and delivery requests within strict time windows using a team of heterogeneous robots. Traditional approaches fail to address dynamic rescheduling or diverse service requirements, typically restricting robots to single-task types. This paper tackles the Multi-Pickup and Delivery Problem with Time Windows (MPDPTW), where autonomous mobile robots are capable of handling varied service requests. The objective is to minimize late delivery penalties while maximizing task completion rates. To achieve this, we propose a novel framework leveraging a heterogeneous robot team and an efficient dynamic scheduling algorithm that supports dynamic task rescheduling. Users submit requests with specific time constraints, and our decentralized algorithm, Heterogeneous Mobile Robots Online Diverse Task Allocation (HMR-ODTA), optimizes task assignments to ensure timely service while addressing delays or task rejections. Extensive simulations validate the algorithm's effectiveness. For smaller task sets (40-160 tasks), penalties were reduced by nearly 63%, while for larger sets (160-280 tasks), penalties decreased by approximately 50%. These results highlight the algorithm's effectiveness in improving task scheduling and coordination in multi-robot systems, offering a robust solution for enhancing delivery performance in structured, time-critical environments.
Impact of Type of Convolution Operation on Performance of Convolutional Neural Networks for Online Signature Verification
(Springer, 2022-11) Gautam, Avinash
An Online signature is a multivariate time series, a commonly used biometric source for user verification. Deep learning (DL) is increasingly becoming ubiquitous as a paradigm for solving problems that come with a wealth of data. Convolution has been its main workhorse. Recently, DL had marked its entry in online signature verification (OSV), a standard bio-metric method that has been mostly dealt with in traditional settings. However, embracing a DL solution to a problem requires certain issues to be tackled, viz. (i) type of convolution, (ii) order of convolution, and (iii) input representation. In this work, we experimentally analyse each of the issues mentioned above regarding OSV, and subsequently present a superior model that reports state-of-the-art (SOTA) performance on three widely used data-sets namely MCYT-100, SVC, and Mobisig. Specifically, the proposed model reports an equal error rate (EER) of 9.72% and 3.1% in Skilled_01 categories of MCYT-100 and SVC data-sets, with gains of around 4% and 3% over the next best performing methods, respectively. The experimental outcome confirms that the interrelationship between the type and order of convolution operation and the input signature representation plays a significant role in the performance of OSV frameworks