Debasish Ghose

Anoop Jain, Debasish Ghose

This paper studies the synchronization of a multi-agent system where the agents are coupled through heterogeneous controller gains. Synchronization refers to the situation where all the agents in a group have a common velocity direction. We generalize existing results and show that by using heterogeneous controller gains, the final velocity direction at which the system of agents synchronize can be controlled. The effect of heterogeneous gains on the reachable set of this final velocity direction is further analyzed. We also show that for realistic systems, a limited control force to stabilize the agents to the synchronized condition can be achieved by confining these heterogeneous controller gains to an upper bound. Simulations are given to support the theoretical findings.

Meenakshi Sarkar, Vinayak Honkote, Dibyendu Das et al.

With the increasing adoption of robots across industries, it is crucial to focus on developing advanced algorithms that enable robots to anticipate, comprehend, and plan their actions effectively in collaboration with humans. We introduce the Robot Autonomous Motion (RoAM) video dataset, which is collected with a custom-made turtlebot3 Burger robot in a variety of indoor environments recording various human motions from the robot's ego-vision. The dataset also includes synchronized records of the LiDAR scan and all control actions taken by the robot as it navigates around static and moving human agents. The unique dataset provides an opportunity to develop and benchmark new visual prediction frameworks that can predict future image frames based on the action taken by the recording agent in partially observable scenarios or cases where the imaging sensor is mounted on a moving platform. We have benchmarked the dataset on our novel deep visual prediction framework called ACPNet where the approximated future image frames are also conditioned on action taken by the robot and demonstrated its potential for incorporating robot dynamics into the video prediction paradigm for mobile robotics and autonomous navigation research.

Anoop Jain, Debasish Ghose

This paper studies the phase balancing of a two and three-agent system where the agents are coupled through heterogeneous controller gains. Balancing refers to the situation in which the movement of agents causes the position of their centroid to become stationary. We generalize existing results and show that by using heterogeneous controller gains, the velocity directions of the agents in balanced formation can be controlled. The effect of heterogeneous gains on the reachable set of these velocity directions is further analyzed. For the two-agents case, the locus of steady-state location of the centroid is also analyzed against the variations in the heterogeneous controller gains. Simulations are given to illustrate the theoretical findings.

Anoop Jain, Debasish Ghose

This paper considers the collective circular motion of multi-agent systems in which all the agents are required to traverse different circles or a common circle at a prescribed angular velocity. It is required to achieve these collective motions with the heading angles of the agents synchronized or balanced. In synchronization, the agents and their centroid have a common velocity direction, while in balancing, the movement of agents causes the location of the centroid to become stationary. The agents considered are initially moving at unit speed around individual circles at different angular velocities. It is assumed that the agents are subjected to limited communication constraints, and exchange relative information according to a time-invariant undirected graph. We present suitable feedback control laws for each of these motion coordination tasks by considering a second-order rotational dynamics of the agent. Simulations are given to illustrate the theoretical findings.

shuvrangshu Jana, Rudrashis Majumder, Aashay Bhise et al.

This paper discusses a Decision Support System (DSS) for cases prediction, allocation of resources, and lockdown management for managing COVID-19 at different levels of a government authority. Algorithms incorporated in the DSS are based on a data-driven modeling approach and independent of physical parameters of the region, and hence the proposed DSS is applicable to any area. Based on predicted active cases, the demand of lower-level units and total availability, allocation, and lockdown decision is made. A MATLAB-based GUI is developed based on the proposed DSS and could be implemented by the local authority.

Meenakshi Sarkar, Devansh Bhardwaj, Debasish Ghose

Stochastic video generation is particularly challenging when the camera is mounted on a moving platform, as camera motion interacts with observed image pixels, creating complex spatio-temporal dynamics and making the problem partially observable. Existing methods typically address this by focusing on raw pixel-level image reconstruction without explicitly modelling camera motion dynamics. We propose a solution by considering camera motion or action as part of the observed image state, modelling both image and action within a multi-modal learning framework. We introduce three models: Video Generation with Learning Action Prior (VG-LeAP) treats the image-action pair as an augmented state generated from a single latent stochastic process and uses variational inference to learn the image-action latent prior; Causal-LeAP, which establishes a causal relationship between action and the observed image frame at time $t$, learning an action prior conditioned on the observed image states; and RAFI, which integrates the augmented image-action state concept into flow matching with diffusion generative processes, demonstrating that this action-conditioned image generation concept can be extended to other diffusion-based models. We emphasize the importance of multi-modal training in partially observable video generation problems through detailed empirical studies on our new video action dataset, RoAM.

Meenakshi Sarkar, Debasish Ghose

Long-term video generation and prediction remain challenging tasks in computer vision, particularly in partially observable scenarios where cameras are mounted on moving platforms. The interaction between observed image frames and the motion of the recording agent introduces additional complexities. To address these issues, we introduce the Action-Conditioned Video Generation (ACVG) framework, a novel approach that investigates the relationship between actions and generated image frames through a deep dual Generator-Actor architecture. ACVG generates video sequences conditioned on the actions of robots, enabling exploration and analysis of how vision and action mutually influence one another in dynamic environments. We evaluate the framework's effectiveness on an indoor robot motion dataset which consists of sequences of image frames along with the sequences of actions taken by the robotic agent, conducting a comprehensive empirical study comparing ACVG to other state-of-the-art frameworks along with a detailed ablation study.

Rajashekhar V S, Debasish Ghose

Mobility, which is a basic property for a mechanism has to be analyzed to find the degrees of freedom. A quick method for calculation of degrees of freedom in a mechanism is proposed in this work. The mechanism is represented in a way that resembles a zebra crossing. An algorithm is proposed which is used to determine the mobility from the zebra crossing diagram. This algorithm takes into account the number of patches between the black patches, the number of joints attached to the fixed link and the number of loops in the mechanism. A number of cases have been discussed which fail to give the desired results using the widely used classical Kutzbach-Grubler formula.

Aditya Hegde, Jasmine Jerry Aloor, Debasish Ghose

The notion of safety in multi-agent systems assumes great significance in many emerging collaborative multi-robot applications. In this paper, we present a multi-UAV collaborative target-tracking application by defining bounded inter-UAV distances in the formation in order to ensure safe operation. In doing so, we address the problem of prioritizing specific objectives over others in a multi-objective control framework. We propose a barrier Lyapunov function-based distributed control law to enforce the bounds on the distances and assess its Lyapunov stability using a kinematic model. The theoretical analysis is supported by numerical results, which account for measurement noise and moving targets. Straight-line and circular motion of the target are considered, and results for quadratic Lyapunov function-based control, often used in multi-agent multi-objective problems, are also presented. A comparison of the two control approaches elucidates the advantages of our proposed safe-control in bounding the inter-agent distances in a formation. A concluding evaluation using ROS simulations illustrates the practical applicability of the proposed control to a pair of multi-rotors visually estimating and maintaining their mutual separation within specified bounds, as they track a moving target.

Lima Agnel Tony, Shuvrangshu Jana, Varun V. P. et al.

This paper presents the design, development, and testing of hardware-software systems by the IISc-TCS team for Challenge 1 of the Mohammed Bin Zayed International Robotics Challenge 2020. The goal of Challenge 1 was to grab a ball suspended from a moving and maneuvering UAV and pop balloons anchored to the ground, using suitable manipulators. The important tasks carried out to address this challenge include the design and development of a hardware system with efficient grabbing and popping mechanisms, considering the restrictions in volume and payload, design of accurate target interception algorithms using visual information suitable for outdoor environments, and development of a software architecture for dynamic multi-agent aerial systems performing complex dynamic missions. In this paper, a single degree of freedom manipulator attached with an end-effector is designed for grabbing and popping, and robust algorithms are developed for the interception of targets in an uncertain environment. Vision-based guidance and tracking laws are proposed based on the concept of pursuit engagement and artificial potential function. The software architecture presented in this work proposes an Operation Management System (OMS) architecture that allocates static and dynamic tasks collaboratively among multiple UAVs to perform any given mission. An important aspect of this work is that all the systems developed were designed to operate in completely autonomous mode. A detailed description of the architecture along with simulations of complete challenge in the Gazebo environment and field experiment results are also included in this work. The proposed hardware-software system is particularly useful for counter-UAV systems and can also be modified in order to cater to several other applications.

Nithya Sridhar, Sai Abhinay. N, Chaithanya Krishna. B et al.

This work proposes a systematic framework for modelling and controller design of a Commercial-Off-The Shelf (COTS) unmanned rotorcraft using control theory and principles, for brick wall construction. With point to point navigation as the primary application, command velocities in the three axes of the Unmanned Aerial Vehicle (UAV) are considered as inputs of the system while its actual velocities are system outputs. Using the sine and step response data acquired from a Hardware-in-Loop (HiL) test simulator, the considered system was modelled in individual axes with the help of the proposed framework. This model was employed for controller design where a sliding mode controller was chosen to satisfy certain requirements of the application like robustness, flexibility and accuracy. The model was validated using step response data and produced a deviation of only 9%. Finally, the controller results from field test showed fine control up to 8 cms accuracy. Sliding Mode Control (SMC) was also compared with a linear controller derived from iterative experimentations and seen to perform better than the latter in terms of accuracy, and robustness to parametric variations and wind disturbances.

B. V. Vidyadhara, Lima Agnel Tony, Mohitvishnu S. Gadde et al.

In this paper, we present a novel passive single Degree-of-Freedom (DoF) manipulator design and its integration on an autonomous drone to capture a moving target. The end-effector is designed to be passive, to disengage the moving target from a flying UAV and capture it efficiently in the presence of disturbances, with minimal energy usage. It is also designed to handle target sway and the effect of downwash. The passive manipulator is integrated with the drone through a single Degree of Freedom (DoF) arm, and experiments are carried out in an outdoor environment. The rack-and-pinion mechanism incorporated for this manipulator ensures safety by extending the manipulator beyond the body of the drone to capture the target. The autonomous capturing experiments are conducted using a red ball hanging from a stationary drone and subsequently from a moving drone. The experiments show that the manipulator captures the target with a success rate of 70\% even under environmental/measurement uncertainties and errors.

Vidyadhara B, Lima Agnel Tony, Mohitvishnu S. Gadde et al.

Grabbing a manoeuvring target using drones is a challenging problem. This paper presents the design, development, and prototyping of a novel aerial manipulator for target interception. It is a single Degree of Freedom (DoF) manipulator with passive basket-type end-effector. The proposed design is energy efficient, light weight and suitable for aerial grabbing applications. The detailed design of the proposed manipulation mechanism and a novel in-flight extending propeller guard, is reported in this paper.

Sarthak J. Shetty, Debasish Ghose

During floods, reaching survivors in the shortest possible time is a priority for rescue teams. Given their ability to explore difficult terrain in short spans of time, Unmanned Aerial Vehicles (UAVs) have become an increasingly valuable aid to search and rescue operations. Traditionally, UAVs utilize exhaustive lawnmower exploration patterns to locate stranded survivors, without any information regarding the survivor's whereabouts. In real life disaster scenarios however, on-ground observers provide valuable information to the rescue effort, such as the survivor's last known location and heading. In earlier work, a Weight Based Exploration (WBE) model, which utilizes this information to generate a prioritized list of waypoints to aid the UAV in its search mission, was proposed. This approach was shown to be effective for a single UAV locating a single survivor. In this paper, we extend the WBE model to a team of UAVs locating multiple survivors. The model initially partitions the search environment amongst the UAVs using Voronoi cells. The UAVs then utilize the WBE model to locate survivors in their partitions. We test this model with varying survivor locations and headings. We demonstrate the scalability of the model developed by testing the model with aerial teams comprising several UAVs.

Rajashekhar V S, Rokesh Laishram, Kaushik Das et al.

In this paper, a 1-DoF gripper mechanism has been synthesized for the type of mechanism, number of links and joints, and the dimensions of length, width and thickness of links. The type synthesis is done by selecting the proper class of mechanism from Reuleaux's six classes of mechanisms. The number synthesis is done by using an algebraic method. The dimensions of the linkages are found using the geometric programming method. The gripper is then modeled in a computer aided design software and then fabricated using an additive manufacturing technique. Finally the gripper mechanism with DC motor as an actuator is mounted on an Unmanned Aerial Vehicle (UAV) to grip a spherical object moving in space. This work is related to a task in challenge 1 of Mohamed Bin Zayed International Robotics Challenge (MBZIRC)-2020.

V. SRajashekhar, M. R. Vibha, Kaushik Das et al.

Aerial transportation requires a simple yet reliable gripper for picking and placing objects of interest. In this work, we design an aerial gripper for passive grasping and impulsive release of ferrous coated objects. Permanent magnets are used for passive grasping and the Scotch Yoke mechanism is used for providing impulsive force to drop the object. The load carrying capacity of the gripper is calculated theoretically and experimentally. The parameters such as the radius of the rotating disk and length of the slider in the Scotch Yoke mechanism were optimized using weighted geometric programming. The dimensions of the gripper mount were derived considering the various components of the gripper. The gripper was mounted on an Unmanned Aerial Vehicle (UAV) and the tests were done by carrying ferrous coated cuboid shaped objects of different sizes and masses. These tests were done in manual and autonomous mode in the outdoor environment.

Lima Agnel Tony, Ashwini Ratnoo, Debasish Ghose

In this article, a novel drone skyway framework called CORRIDRONE is proposed. As the name suggests, this represents virtual air corridors for point-to-point safe passage of multiple drones. The corridors are not permanent but can be set up on demand. A few such scenarios could be those in warehouse/factory floors, package delivery, shore-to-ship delivery, border patrol, etc. Several factors play major roles in the planning and design of such aerial passages. The proposed framework includes many novel features which aid safe and efficient integration of UAVs into the airspace with already available technologies. A several kilometres long test bed is proposed to be set-up at the 1500 acres Challekere campus of Indian Institute of Science, in the state of Karnataka, to design and test the infrastructure required for CORRIDRONE.

Aashay Bhise, Shuvrangshu Jana, Lima Agnel Tony et al.

Accurate estimation and prediction of trajectory is essential for interception of any high speed target. In this paper, an extended Kalman filter is used to estimate the current location of target from its visual information and then predict its future position by using the observation sequence. Target motion model is developed considering the approximate known pattern of the target trajectory. In this work, we utilise visual information of the target to carry out the predictions. The proposed algorithm is developed in ROS-Gazebo environment and is verified using hardware implementation.

Lima Agnel Tony, Shuvrangshu Jana, Varun V P et al.

This work details the problem of aerial target capture using multiple UAVs. This problem is motivated from the challenge 1 of Mohammed Bin Zayed International Robotic Challenge 2020. The UAVs utilise visual feedback to autonomously detect target, approach it and capture without disturbing the vehicle which carries the target. Multi-UAV collaboration improves the efficiency of the system and increases the chance of capturing the ball robustly in short span of time. In this paper, the proposed architecture is validated through simulation in ROS-Gazebo environment and is further implemented on hardware.

Lima Agnel Tony, Shuvrangshu Jana, Aashay Bhise et al.

Selective interception of objects in unknown environment autonomously by UAVs is an interesting problem. In this work, vision based interception is carried out. This problem is a part of challenge 1 of Mohammed Bin Zayed International Robotic Challenge, 2020, where, balloons are kept at five random locations for the UAVs to autonomously explore, detect, approach and intercept. The problem requires a different formulation to execute compared to the normal interception problems in literature. This work details the different aspect of this problem from vision to manipulator design. The frame work is implemented on hardware using Robot Operating System (ROS) communication architecture.

Kumar Ankit, Lima Agnel Tony, Shuvrangshu Jana et al.

This paper details the algorithms involved and task planner for vehicle collaboration in building a structure. This is the problem defined in challenge 2 of Mohammed Bin Zayed International Robotic Challenge 2020 (MBZIRC). The work addresses various aspects of the challenge for Unmanned Aerial Vehicles (UAVs) and Unmanned Ground Vehicle (UGV). The challenge involves repeated pick and place operations using UAVs and UGV to build two structures of different shape and sizes. The algorithms are implemented using the Robot Operating System (ROS) framework and visualised in Gazebo. The whole developed architecture could readily be implemented in suitable hardware.

Aakriti Agrawal, Aashay Bhise, Rohitkumar Arasanipalai et al.

Accurate estimation and prediction of trajectory is essential for the capture of any high speed target. In this paper, an extended Kalman filter (EKF) is used to track the target in the first loop of the trajectory to collect data points and then a combination of machine learning with least-square curve-fitting is used to accurately estimate future positions for the subsequent loops. The EKF estimates the current location of target from its visual information and then predicts its future position by using the observation sequence. We utilize noisy visual information of the target from the three dimensional trajectory to carry out the predictions. The proposed algorithm is developed in ROS-Gazebo environment and is implemented on hardware.

Aakriti Agrawal, V S Rajashekhar, Rohitkumar Arasanipalai et al.

A terrestrial robot that can maneuver rough terrain and scout places is very useful in mapping out unknown areas. It can also be used explore dangerous areas in place of humans. A terrestrial robot modeled after a scorpion will be able to traverse undetected and can be used for surveillance purposes. Therefore, this paper proposes modelling of a scorpion inspired robot and a reinforcement learning (RL) based controller for navigation. The robot scorpion uses serial four bar mechanisms for the legs movements. It also has an active tail and a movable claw. The controller is trained to navigate the robot scorpion to the target waypoint. The simulation results demonstrate efficient navigation of the robot scorpion.

Sarthak J. Shetty, Rahul Ravichandran, Lima Agnel Tony et al.

Survivors stranded during floods tend to seek refuge on dry land. It is important to search for these survivors and help them reach safety as quickly as possible. The terrain in such situations however, is heavily damaged and restricts the movement of emergency personnel towards these survivors. Therefore, it is advantageous to utilize Unmanned Aerial Vehicles (UAVs) in cooperation with on-ground first responders to aid search and rescue efforts. In this article we demonstrate an implementation and improvement of the weight-based path planning algorithm using an off-the-shelf UAV. The coordinates of the survivor and their heading is reported by an on-ground observer to the UAV to generate a weighted map of the surroundings for exploration. Each coordinate in the map is assigned a weight which dictates the priority of exploration. These waypoints are then sorted on the basis of their weights to arrive at an ordered list for exploration by the UAV. We developed the model in MATLAB, followed by prototyping on Robot Operating System (ROS) using a 3DR Iris quadcopter. We tested the model on an off-the-shelf UAV by utilizing the MAVROS and MAVLINK capabilities of ROS. During the implementation of the algorithm on the UAV, several additional factors such as unreliable GPS signals and limited field of view which could effect the performance of the model were in effect, despite which the algorithm performed fairly well. We compared our model with conventional algorithms described in the literature, and showed that our implementation outperforms them.

Rohitkumar Arasanipalai, Aakriti Agrawal, Debasish Ghose

Quadcopters can suffer from loss of propellers in mid-flight, thus requiring a need to have a system that detects single and multiple propeller failures and an adaptive controller that stabilizes the propeller-deficient quadcopter. This paper presents reinforcement learning based controllers for quadcopters with 4, 3, and 2 (opposing) functional propellers. The paper also proposes a neural network based propeller fault detection system to detect propeller loss and switch to the appropriate controller. The simulation results demonstrate a stable quadcopter with efficient waypoint tracking for all controllers. The detection system is able to detect propeller failure in a short time and stabilize the quadcopter.

Meenakshi Sarkar, Prabhu Pradhan, Debasish Ghose

In this paper, we introduce a novel framework that can learn to make visual predictions about the motion of a robotic agent from raw video frames. Our proposed motion prediction network (PROM-Net) can learn in a completely unsupervised manner and efficiently predict up to 10 frames in the future. Moreover, unlike any other motion prediction models, it is lightweight and once trained it can be easily implemented on mobile platforms that have very limited computing capabilities. We have created a new robotic data set comprising LEGO Mindstorms moving along various trajectories in three different environments under different lighting conditions for testing and training the network. Finally, we introduce a framework that would use the predicted frames from the network as an input to a model predictive controller for motion planning in unknown dynamic environments with moving obstacles.

Titas Bera, M. Seetharama Bhat, Debasish Ghose

Sampling based planners have been successful in robot motion planning, with many degrees of freedom, but still remain ineffective in the presence of narrow passages within the configuration space. There exist several heuristics, which generate samples in the critical regions and improve the efficiency of probabilistic roadmap planners. In this paper, we present an evaluation of success probability of one such heuristic method, called obstacle based probabilistic roadmap planners or OBPRM, using geometric probability theory. The result indicates that the probability of success of generating free sample points around the surface of the $n$ dimensional configuration space obstacle is directly proportional to the surface area of the obstacles.

Meenakshi Sarkar, Debasish Ghose

Predicting movement of objects while the action of learning agent interacts with the dynamics of the scene still remains a key challenge in robotics. We propose a multi-layer Long Short Term Memory (LSTM) autoendocer network that predicts future frames for a robot navigating in a dynamic environment with moving obstacles. The autoencoder network is composed of a state and action conditioned decoder network that reconstructs the future frames of video, conditioned on the action taken by the agent. The input image frames are first transformed into low dimensional feature vectors with a pre-trained encoder network and then reconstructed with the LSTM autoencoder network to generate the future frames. A virtual environment, based on the OpenAi-Gym framework for robotics, is used to gather training data and test the proposed network. The initial experiments show promising results indicating that these predicted frames can be used by an appropriate reinforcement learning framework in future to navigate around dynamic obstacles.

Titas Bera, Debasish Ghose, Sundaram Suresh

In this paper we investigate the asymptotic optimality property of a randomized sampling based motion planner, namely RRT. We prove that a RRT planner is not an asymptotically optimal motion planner. Our result, while being consistent with similar results which exist in the literature, however, brings out an important characteristics of a RRT planner. We show that the degree distribution of the tree vertices follows a power law in an asymptotic sense. A simulation result is presented to support the theoretical claim. Based on these results we also try to establish a simple necessary condition for sampling based motion planners to be asymptotically optimal.

Esh Vckay, Debasish Ghose

We present a new social animal inspired emotional swarm intelligence technique. This technique is used to solve a variant of the popular collective robots problem called foraging. We show with a simulation study how simple interaction rules based on sensations like hunger and loneliness can lead to globally coherent emergent behavior which allows sensor constrained robots to solve the given problem

K. R. Guruprasad, Debasish Ghose

In this paper a generalization of the Voronoi partition is used for optimal deployment of autonomous agents carrying sensors with heterogeneous capabilities, to maximize the sensor coverage. The generalized centroidal Voronoi configuration, in which the agents are located at the centroids of the corresponding generalized Voronoi cells, is shown to be a local optimal configuration. Simulation results are presented to illustrate the presented deployment strategy.