Ranshaa's starred repositories
Futures-forecast-PSO-SVM
利用PSO优化的SVM进行期货预测
multiclassSVM
Experiments on creating an SVM that can perform multi-class classification
pythermalcomfort
Package to calculate several thermal comfort indices (e.g. PMV, PPD, SET, adaptive) and convert physical variables.
-Adaptive-Filtering-Technique-for-Error-Detection-and-Correction-of-Precision-Welding-RobotAdaptive-
Robotics and Automation have played a major role in the field of automobile manufacturing, space research, logistics, agriculture and many more. One such robot is a welding robot which is programmed to weld a product in the automotive industry. These robots are very accurate and don’t have any errors. But, sometimes due to some vibrations in the motors or due to any external factors, the robot may deviate from its specified position which leads to defective welding of a product. The robot arm is subjected to object tracking. The position of the robot arm is tracked by mounting an accelerometer on the robot arm. This position deviation can be corrected by using Kalman filtering technique. Kalman filters are used in the field of robotics motion planning, control and trajectory optimization. A com-mon application is for state prediction and estimation, object tracking. This paper is about applying Kalman filtering technique to a three-axis accelerometer which is mounted on the robotic arm of a welding robot. The voltage values of the accelerometer sensor are taken for state prediction and by recursive iterations the values are optimized such that error becomes minimum when the robot has deviated from its desired position.
RRT-Path-Planning
An RRT path planning algorithm in MATLAB that calculates 100 paths through a known field with obstacles to reach the endzone. The program utilizes Kalman Filter to track uncertainty. The program produces 3 plots: the shortest path, path with least uncertainty, and the path with greatest uncertainty.
KernelTrajectoryMaps
Kernel Trajectory Maps CoRL 2019
Trajectory-Prediction
A robust tracking approach to trajectory prediction for vehicles
vehicle-trajectory-prediction
Behavior Prediction in Autonomous Driving
Prediction-Phase-in-the-trajectory-generation-of-cars
In general, the way we think about handling multi-modal uncertainty is by maintaining some beliefs about how probable each potential mode is.
trajectory-prediction-for-KalmanPrediction-and-DeepLearning
This repository is for studying a trajectory prediction using Kalman filter and deep learning models.
Trajectories-Prediction-Kalman
Study of trajectories Prediction with Kalman Filter
probability-collision
Calculate the probability of two self-driving cars colliding at an intersection
deep-ensembles
Reproduction of the paper: Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
vehicle_trajectory_prediction_combined_with_behavior_recognition
A vehicle trajectory prediction combined with vehicle behavior recognition,and propose an acceleration trajectory optimization algorithm.
Motion-Prediction-of-Agents-in-the-Vicinity-of-Self-Driving-Car
The goal of the project was to predict the motion of an autonomous vehicle and the surrounding agents given their trajectory for the past one second. For this, we used rasterized images as an input to a CNN baseline. To the given parameters, we added the velocities along x and y direction. This helped predicting instantaneous velocity of the agent at every time step. In addition, the baseline was modified by adding an LSTM decoder to study their impact on predictions. Instantaneous velocity was an added parameter for the model and predicting instantaneous velocities can be used to improve the motion prediction of the agents and can facilitate agent interaction and cooperative driving
LSTM_Trajectory_Prediction
Using LSTM to predict the path of the driverless vehicle
LSTM-for-Trajectory-Prediction
LSTM based Vehicle Trajectory Prediction
MotionPlanning
Motion planning algorithms commonly used on autonomous vehicles. (path planning + path tracking)