10 skills found
MRPT / Mrpt:zap: The Mobile Robot Programming Toolkit (MRPT)
ACFR-RPG / DynOSAMOffical code release for DynoSAM: Dynamic Object Smoothing And Mapping. Accepted Transactions on Robotics (Visual SLAM SI). A visual SLAM framework and pipeline for Dynamic environements, estimating for the motion/pose of objects and their structure, as well as the camera odometry and static map.
JuliaRobotics / RoME.jlRobot Motion Estimate: Tools, Variables, and Factors for SLAM in robotics; also see Caesar.jl.
kimkimyoung / Exoskeleton RBFNNDuring the exoskeleton robot project, we integrate sensors system with radius basic function nerual network to estimate the human motion intention
Mattral / Kalman Filter Mpu6050implements a 2D Kalman filter for estimating roll and pitch angles of an object based on data from a gyroscope and accelerometer. The application of this code is in stabilizing and smoothing orientation measurements, often used in robotics, drones, and various motion control systems.
balthazarneveu / Monocular Pose And Forces EstimationReview of the paper "Estimating 3D Motion and Forces of Person-Object Interactions from Monocular Video" MVA Robotics class 2023
sseshadr / Auvsi Cv MotionEstimationLearn how we perceive motion and how to estimate motion using a technique called Optical Flow. You can use three algorithms to implement optical flow using the Computer Vision Toolbox. These three algorithms are Horn-Schunck method, Farneback method, and Lucas-Kanade method. An example of a robot boat moving through a field of buoys will be used.
chetangadidesi / EKF LocalizationA Python project for mobile robot localization using the Extended Kalman Filter (EKF). Simulates robot motion, GPS measurements, and dead reckoning to estimate position in 2D space with real-time visualization.
ngowtham1296 / Model Estimation Of Non Linear Dynamical SystemThe stochastic approach to predict the model estimation is a recently introduced control strategy for the underactuated systems (hopping robot) that allows the system to predict its trajectory movements in the unpredicted environment. In this work, we demonstrate the stochastic approach through Machine Learning technique (Gaussian Mixture Model) which allows us to predict the state information by interpreting with the sample state information of the Hopping robot through a probabilistic approach. The output of this approach will yield us with the desired estimated state of the system. Finally, we are going to hand over our work for applying this estimated policy to the simulated Hopping robot by using an Iterative Linear Quadratic Regulator (iLQR) as a controller which updates the predicted model estimation to the existing control policy of the system to determine its optimal trajectory motion.
Pradeep-Gopal / Visual Odometry Self Driving CarsVisual odometry is used for estimating the trajectory of the robot. In this project we have been given a data set with frames of a driving sequence taken by a camera in a car. We are to estimate the 3D motion of the camera and provide a plot of the trajectory of the camera. We have been given the scripts to extract the intrinsic parameters using which the essential and Fundamental matrices can be calculated. Using this we compute the rotation and translation components thus estimating the 3D motion.
