Browsing by Author "Upadhyay, Saurabh"

Now showing 1 - 6 of 6
  • Thumbnail Image
    ItemOpen Access
    A causal learning approach to in-orbit inertial parameter estimation for multi-payload deployers
    (International Astronautical Federation (IAF), 2024-10-18) Platanitis, Konstantinos; Arana-Catania, Miguel; Upadhyay, Saurabh; Felicetti, Leonard
    This paper discusses an approach to inertial parameter estimation for the case of cargo carrying spacecraft that is based on causal learning, i.e. learning from the responses of the spacecraft, under actuation. Different spacecraft configurations (inertial parameter sets) are simulated under different actuation profiles, in order to produce an optimised time-series clustering classifier that can be used to distinguish between them. The actuation is comprised of finite sequences of constant inputs that are applied in order, based on typical actuators available. By learning from the system’s responses across multiple input sequences, and then applying measures of time-series similarity and F1-score, an optimal actuation sequence can be chosen either for one specific system configuration or for the overall set of possible configurations. This allows for both estimation of the inertial parameter set without any prior knowledge of state, as well as validation of transitions between different configurations after a deployment event. The optimisation of the actuation sequence is handled by a reinforcement learning model that uses the proximal policy optimisation (PPO) algorithm, by repeatedly trying different sequences and evaluating the impact on classifier performance according to a multi-objective metric.
  • Thumbnail Image
    ItemOpen Access
    A collaborative robotic system for entering and mapping Martian caves
    (International Astronautical Federation (IAF), 2024-10-18) Devaguptapu, Venkata; Elsayed, Abdulla; Ferreyra, Marie; Guichandut, Thibault; James, Ajina; Laguelle, Aurore; Maniraj, Krishna Priya; Mouchot, Axel; Nair, Aditi; Palange, Mihir; Shufflebotham, Alex; Felicetti, Leonard; Upadhyay, Saurabh; Weclewski, Piotr
    Martian caves represent prime locations for investigating evidence of extinct or extant life. In this paper, we propose a technology demonstration mission for Martian cave exploration using a heterogeneous robotic system. Heterogeneous systems are advantageous for Martian cave exploration due to their specialisation for specific tasks, flexibility, and adaptability to diverse conditions. Our mission focuses on the exploration of type 1 atypical pit crater caves in the Elysium Mons region due to their scientific value regarding the potential existence of life and ice water deposits. These caves, situated near the equator, offer low elevation and reduced radiation effects, ensuring safer landing conditions and high scientific outputs. Our mission considers the design of a robotic system capable of entering and mapping the cave environment under five work packages (System, Mission, Payload, Electrical and Mechanical). A risk analysis, concept of operations and budget were established to make sure the requirements and objectives of the mission were fulfilled. To accomplish this mission, we have traded-off different rover locomotion concepts and selected a heterogeneous robotic system comprising a wheeled rover and a multi-rotor aerial robot in a parent-child configuration. The mission is defined in multiple phases starting with the traversal of the wheeled rover and the aerial robot from the landing site to the selected cave. Once at the cave entrance, the rover scans the circumference, and the aerial robot goes into the cave through the entrance to map it. The aerial robot will use a Simultaneous Localisation and Mapping (SLAM) algorithm along with a LIDAR to map and navigate the cave’s interior. The wheeled rover (parent ship), powered by solar arrays, serves as a communication and recharging station at the cave entrance. Using a docking station, it will enable the aerial robot to recharge and communicate with Earth. The cave entry and mapping are demonstrated with a simulation to test the viability of the proposed approach. The proposed autonomy of the heterogeneous robotic system is demonstrated using simulation results in MATLAB Simulink.
  • Thumbnail Image
    ItemOpen Access
    Autonomous robotic arm manipulation for planetary missions using causal machine learning
    (European Space Agency (ESA), 2023-10-20) McDonnell, Cian; Arana-Catania, Miguel; Upadhyay, Saurabh
    Autonomous robotic arm manipulators have the potential to make planetary exploration and in-situ resource utilization missions more time efficient and productive, as the manipulator can handle the objects itself and perform goal-specific actions. We train a manipulator to autonomously study objects of which it has no prior knowledge, such as planetary rocks. This is achieved using causal machine learning in a simulated planetary environment. Here, the manipulator interacts with objects, and classifies them based on differing causal factors. These are parameters, such as mass or friction coefficient, that causally determine the outcomes of its interactions. Through reinforcement learning, the manipulator learns to interact in ways that reveal the underlying causal factors. We show that this method works even without any prior knowledge of the objects, or any previously collected training data. We carry out the training in planetary exploration conditions, with realistic manipulator models.
  • Thumbnail Image
    ItemOpen Access
    Implementation of a federated laboratories network for testing formation flying technologies
    (International Astronautical Federation (IAF), 2024-10-18) Sabatini, Marco; Felicetti, Leonard; Shufflebotham, Alex; Leslie, Cameron; Upadhyay, Saurabh; Platanitis, Konstantinos; Laufer, Rene; Persson, Olle; Rao Ramavaram, Harish
    Formations of microsatellites are a highly attractive solution for achieving responsive space missions focused on Earth observation and communication support, due to their low cost and mass. However, operating these formations is challenging and requires extensive testing, which can be difficult to carry out due to the need for multiple platforms and large testing spaces. This paper presents the first concept and the first steps of a research program funded by NATO in the framework of the Science for Peace and Security program, with the specific purpose to develop and evaluate the necessary infrastructure for establishing a virtual, multi-platform distributed laboratory network comprised of laboratories from Sapienza, Lulea and Cranfield Universties. The value of this network will be increased by sharing resources, equipment, and expertise among the participating laboratories.
  • Thumbnail Image
    ItemOpen Access
    A ROS-based simulation and control framework for in-orbit multi-arm robot assembly operations
    (European Space Agency (ESA), 2023-10-20) Bhadani, Saksham; Dillikar, Sairaj R.; Pradhan, Omkar N.; Cotrina de los Mozos, Irene; Felicetti, Leonard; Upadhyay, Saurabh; Tang, Gilbert
    This paper develops a simulation and control framework for a multi-arm robot performing in-orbit assembly. The framework considers the robot locomotion on the assembled structure, the assembly planning, and multi-arm control. An inchworm motion is mimicked using a sequential docking approach to achieve locomotion. An RRT* based approach is implemented to complete the sequential assembly as well as the locomotion of MARIO across the structure. A semi-centralised controller model is used to control the robotic arms for these operations. The architecture uses MoveIt! libraries, Gazebo simulator and Python to simulate the desired locomotion and assembly tasks. The simulation results validate the viability of the developed framework.
  • Thumbnail Image
    ItemOpen Access
    Trajectory shaping guidance for impact angle control of planetary hopping robots
    (Frontiers, 2024-11-11) Mondal, Sabyasachi; Upadhyay, Saurabh
    This paper presents a novel optimal trajectory-shaping control concept for a planetary hopping robot. The hopping robot suffers from uncontrolled in-flight and undesired after-landing motions, leading to a position drift at landing. The proposed concept thrives on the Generalized Vector Explicit (GENEX) guidance, which can generate and shape the optimal trajectory and satisfy the end-point constraints like the impact angle of the velocity vector. The proposed concept is used for a thruster-based hopping robot, which achieves a range of impact angles, reduces the position drift at landing due to the undesired in-flight and after-landing motions, and handles the error in initial hopping angles. The proposed approach’s conceptual realization is illustrated by lateral acceleration generated using thruster orientation control. Extensive simulations are carried out on horizontal and sloped surfaces with different initial and impact angle conditions to demonstrate the effect of impact angle on the position drift error and the viability of the proposed approach.