Shyam Sundar Kannan

Shyam Sundar Kannan, Byung-Cheol Min

Scene Change Detection is a challenging task in computer vision and robotics that aims to identify differences between two images of the same scene captured at different times. Traditional change detection methods rely on training models that take these image pairs as input and estimate the changes, which requires large amounts of annotated data, a costly and time-consuming process. To overcome this, we propose ZeroSCD, a zero-shot scene change detection framework that eliminates the need for training. ZeroSCD leverages pre-existing models for place recognition and semantic segmentation, utilizing their features and outputs to perform change detection. In this framework, features extracted from the place recognition model are used to estimate correspondences and detect changes between the two images. These are then combined with segmentation results from the semantic segmentation model to precisely delineate the boundaries of the detected changes. Extensive experiments on benchmark datasets demonstrate that ZeroSCD outperforms several state-of-the-art methods in change detection accuracy, despite not being trained on any of the benchmark datasets, proving its effectiveness and adaptability across different scenarios.

Shyam Sundar Kannan, Byung-Cheol Min

Visual place recognition is a challenging task in the field of computer vision, and autonomous robotics and vehicles, which aims to identify a location or a place from visual inputs. Contemporary methods in visual place recognition employ convolutional neural networks and utilize every region within the image for the place recognition task. However, the presence of dynamic and distracting elements in the image may impact the effectiveness of the place recognition process. Therefore, it is meaningful to focus on task-relevant regions of the image for improved recognition. In this paper, we present PlaceFormer, a novel transformer-based approach for visual place recognition. PlaceFormer employs patch tokens from the transformer to create global image descriptors, which are then used for image retrieval. To re-rank the retrieved images, PlaceFormer merges the patch tokens from the transformer to form multi-scale patches. Utilizing the transformer's self-attention mechanism, it selects patches that correspond to task-relevant areas in an image. These selected patches undergo geometric verification, generating similarity scores across different patch sizes. Subsequently, spatial scores from each patch size are fused to produce a final similarity score. This score is then used to re-rank the images initially retrieved using global image descriptors. Extensive experiments on benchmark datasets demonstrate that PlaceFormer outperforms several state-of-the-art methods in terms of accuracy and computational efficiency, requiring less time and memory.

Manoj Penmetcha, Shyam Sundar Kannan, Byung-Cheol Min

Many robotic applications that are critical for robot performance require immediate feedback, hence execution time is a critical concern. Furthermore, it is common that robots come with a fixed quantity of hardware resources; if an application requires more computational resources than the robot can accommodate, its onboard execution might be extended to a degree that degrades the robot performance. Cloud computing, on the other hand, features on-demand computational resources; by enabling robots to leverage those resources, application execution time can be reduced. The key to enabling robot use of cloud computing is designing an efficient offloading algorithm that makes optimum use of the robot onboard capabilities and also forms a quick consensus on when to offload without any prior knowledge or information about the application. In this paper, we propose a predictive algorithm to anticipate the time needed to execute an application for a given application data input size with the help of a small number of previous observations. To validate the algorithm, we train it on the previous N observations, which include independent (input data size) and dependent (execution time) variables. To understand how algorithm performance varies in terms of prediction accuracy and error, we tested various N values using linear regression and a mobile robot path planning application. From our experiments and analysis, we determined the algorithm to have acceptable error and prediction accuracy when N>40.

Shyam Sundar Kannan, Ahreum Lee, Byung-Cheol Min

External Human-Machine Interfaces (eHMI) are widely used on robots and autonomous vehicles to convey the machine's intent to humans. Delivery robots are getting common, and they share the sidewalk along with the pedestrians. Current research has explored the design of eHMI and its effectiveness for social robots and autonomous vehicles, but the use of eHMIs on delivery robots still remains unexplored. There is a knowledge gap on the effective use of eHMIs on delivery robots for indicating the robot's navigational intent to the pedestrians. An online survey with 152 participants was conducted to investigate the comprehensibility of the display and light-based eHMIs that convey the delivery robot's navigational intent under common navigation scenarios. Results show that display is preferred over lights in conveying the intent. The preferred type of content to be displayed varies according to the scenarios. Additionally, light is preferred as an auxiliary eHMI to present redundant information. The findings of this study can contribute to the development of future designs of eHMI on delivery robots.

Shyam Sundar Kannan, Byung-Cheol Min

In this work, we present a system that enables delivery drones to autonomously navigate and deliver packages at various locations around a house according to the desire of the recipient and without the need for any external markers as currently used. This development is motivated by recent advancements in deep learning that can potentially supplant the specialized markers presently used by delivery drones for identifying sites at which to deliver packages. The proposed system is more natural in that it takes instruction on where to deliver the package as input, similar to the instructions provided to human couriers. First, we propose a semantic image segmentation-based descending location estimator that enables the drone to find a safe spot around the house at which it can descend from higher altitudes. Following this, we propose a strategy for visually routing the drone from the descent location to a specific site at which it is to deliver the package, such as the front door. We extensively evaluate this approach in a simulated environment and demonstrate that with our system, a delivery drone can deliver a package to the front door and also to other specified locations around a house. Relative to a frontier exploration-based strategy, drones using the proposed system found and reached the front doors of the 20 test houses 161% faster.

Tamzidul Mina, Shyam Sundar Kannan, Wonse Jo et al.

Multi-human multi-robot (MH-MR) systems have the ability to combine the potential advantages of robotic systems with those of having humans in the loop. Robotic systems contribute precision performance and long operation on repetitive tasks without tiring, while humans in the loop improve situational awareness and enhance decision-making abilities. A system's ability to adapt allocated workload to changing conditions and the performance of each individual (human and robot) during the mission is vital to maintaining overall system performance. Previous works from literature including market-based and optimization approaches have attempted to address the task/workload allocation problem with focus on maximizing the system output without regarding individual agent conditions, lacking in real-time processing and have mostly focused exclusively on multi-robot systems. Given the variety of possible combination of teams (autonomous robots and human-operated robots: any number of human operators operating any number of robots at a time) and the operational scale of MH-MR systems, development of a generalized framework of workload allocation has been a particularly challenging task. In this paper, we present such a framework for independent homogeneous missions, capable of adaptively allocating the system workload in relation to health conditions and work performances of human-operated and autonomous robots in real-time. The framework consists of removable modular function blocks ensuring its applicability to different MH-MR scenarios. A new workload transition function block ensures smooth transition without the workload change having adverse effects on individual agents. The effectiveness and scalability of the system's workload adaptability is validated by experiments applying the proposed framework in a MH-MR patrolling scenario with changing human and robot condition, and failing robots.

Ahreum Lee, Wonse Jo, Shyam Sundar Kannan et al.

Multi-robot systems are made up of a team of multiple robots, which provides the advantage of performing complex tasks with high efficiency, flexibility, and robustness. Although research on human-robot interaction is ongoing as robots become more readily available and easier to use, the study of interactions between a human and multiple robots represents a relatively new field of research. In particular, how multi-robots could be used for everyday users has not been extensively explored. Additionally, the impact of the characteristics of multiple robots on human perception and cognition in human multi-robot interaction should be further explored. In this paper, we specifically focus on the benefits of physical affordances generated by the movements of multi-robots, and investigate the effects of deictic movements of multi-robots on information retrieval by conducting a delayed free recall task.

Wonse Jo, Shyam Sundar Kannan, Go-Eum Cha et al.

This paper presents a framework for monitoring human and robot conditions in human multi-robot interactions. The proposed framework consists of four modules: 1) human and robot conditions monitoring interface, 2) synchronization time filter, 3) data feature extraction interface, and 4) condition monitoring interface. The framework is based on Robot Operating System (ROS), and it supports physiological and behavioral sensors and devices and robot systems, as well as custom programs. Furthermore, it allows synchronizing the monitoring conditions and sharing them simultaneously. In order to validate the proposed framework, we present experiment results and analysis obtained from the user study where 30 human subjects participated and simulated robot experiments.

Manoj Penmetcha, Shyam Sundar Kannan, Byung-Cheol Min

Robots have inherently limited onboard processing, storage, and power capabilities. Cloud computing resources have the potential to provide significant advantages for robots in many applications. However, to make use of these resources, frameworks must be developed that facilitate robot interactions with cloud services. In this paper, we propose a cloud-based architecture called Smart Cloud that intends to overcome the physical limitations of single- or multi-robot systems through massively parallel computation, provided on demand by cloud services. Smart Cloud is implemented on Amazon Web Services (AWS) and available for robots running on the Robot Operating System (ROS) and on the non-ROS systems. Smart Cloud features a first-of-its-kind architecture that incorporates JavaScript-based libraries to run various robotic applications related to machine learning and other methods. This paper presents the architecture and its performance in terms of CPU usage and latency, and finally validates it for navigation and machine learning applications.

Shyam Sundar Kannan, Wonse Jo, Ramviyas Parasuraman et al.

In this paper, we propose an autonomous exploration and a tapping mechanism-based material mapping system for a mobile robot in unknown environments. The goal of the proposed system is to integrate simultaneous localization and mapping (SLAM) modules and sound-based material classification to enable a mobile robot to explore an unknown environment autonomously and at the same time identify the various objects and materials in the environment. This creates a material map that localizes the various materials in the environment which has potential applications for search and rescue scenarios. A tapping mechanism and tapping audio signal processing based on machine learning techniques are exploited for a robot to identify the objects and materials. We demonstrate the proposed system through experiments using a mobile robot platform installed with Velodyne LiDAR, a linear solenoid, and microphones in an exploration-like scenario with various materials. Experiment results demonstrate that the proposed system can create useful material maps in unknown environments.