This work is aimed to demonstrate a multi-objective joint trajectory generation algorithm for a 7 degree of freedom (DoF) robotic manipulator using swarm intelligence (SI)—product of exponentials (PoE) combination. Given a priori knowledge of the end-effector Cartesian trajectory and obstacles in the workspace, the inverse kinematics problem is tackled by SI-PoE subject to multiple constraints. The algorithm is designed to satisfy finite jerk constraint on end-effector, avoid obstacles, and minimize control effort while tracking the Cartesian trajectory. The SI-PoE algorithm is compared with conventional inverse kinematics algorithms and standard particle swarm optimization (PSO). The joint trajectories produced by SI-PoE are experimentally tested on Sawyer 7 DoF robotic arm, and the resulting torque trajectories are compared.

No abstract

The foundation and emphasis of robotic manipulator control is Inverse Kinematics (IK). Due to the complexity of derivation, difficulty of computation, and redundancy, traditional IK solutions pose numerous challenges to the operation of a variety of robotic manipulators. This paper develops a Deep Reinforcement Learning (RL) approach for solving the IK problem of a 7-Degree of Freedom (DOF) robotic manipulator using Product of Exponentials (PoE) as a Forward Kinematics (FK) computation tool and the Deep Q-Network (DQN) as an IK solver. The selected approach is architecturally simpler, making it faster and easier to implement, as well as more stable, because it is less sensitive to hyperparameters than continuous action spaces algorithms. The algorithm is designed to produce joint-space trajectories from a given end-effector trajectory. Different network architectures were explored and the output of the DQN was implemented experimentally on a Sawyer robotic arm. The DQN was able to find different trajectories corresponding to a specified Cartesian path of the end-effector. The network agent was able to learn random Bézier and straight-line end-effector trajectories in a reasonable time frame with good accuracy, demonstrating that even though DQN is mainly used in discrete solution spaces, it could be applied to generate joint space trajectories.

No abstract

This work utilizes a MobileNetV2 Convolutional Neural Network (CNN) for fast, mobile detection of satellites, and rejection of stars, in cluttered unresolved space imagery. First, a custom database is created using imagery from a synthetic satellite image program and labeled with bounding boxes over satellites for "satellitepositive" images. The CNN is then trained on this database and the inference is validated by checking the accuracy of the model on an external dataset constructed of real telescope imagery. In doing so, the trained CNN provides a method of rapid satellite identification for subsequent utilization in ground-based orbit estimation.