Realtime autonomous navigation in V-Rep based static and dynamic environment using EKF-SLAM

<p>Localization in an autonomous mobile robot allows it to operate autonomously in an unknown and unpredictable environment with the ability to determine its position and heading. Simultaneous localization and mapping (SLAM) are introduced to solve the problem where no prior information about the environment is available either static or dynamic to achieve standard map-based localization. The primary focus of this research is autonomous mobile robot navigation using the extended Kalman filter (EKF)-SLAM environment modeling technique which provides higher accuracy and reliability in mobile robot localization and mapping results. In this paper, EKF-SLAM performance is verified by simulations performed in a static and dynamic environment designed in V-REP i.e., 3D Robot simulation environment. In this work SLAM problem of two-wheeled differential drive robot i.e., Pioneer 3-DX in indoor static and dynamic environment integrated with Laser range finder i.e., Hokuyo URG-04LX- UG01, LIDAR, and Ultrasonic sensors is solved. EKF-SLAM scripts are developed using MATLAB that is linked to V-REP via remote API feature to evaluate EKF-SLAM performance. The reached results confirm the EKF- SLAM is a reliable approach for real-time autonomous navigation for mobile robots in comparison to other techniques.</p>

Unsupervised deep learning based ego motion estimation with a downward facing camera

Knowing the robot's pose is a crucial prerequisite for mobile robot tasks such as collision avoidance or autonomous navigation. Using powerful predictive models to estimate transformations for visual odometry via downward facing cameras is an understudied area of research. This work proposes a novel approach based on deep learning for estimating ego motion with a downward looking camera. The network can be trained completely unsupervised and is not restricted to a specific motion model. We propose two neural network architectures based on the Early Fusion and Slow Fusion design principle: “EarlyBird” and “SlowBird”. Both networks share a Spatial Transformer layer for image warping and are trained with a modified structural similarity index (SSIM) loss function. Experiments carried out in simulation and for a real world differential drive robot show similar and partially better results of our proposed deep learning based approaches compared to a state-of-the-art method based on fast Fourier transformation.

Staircase Detection, Characterization and Approach Pipeline for Search and Rescue Robots

Currently, most rescue robots are mainly teleoperated and integrate some level of autonomy to reduce the operator’s workload, allowing them to focus on the primary mission tasks. One of the main causes of mission failure are human errors and increasing the robot’s autonomy can increase the probability of success. For this reason, in this work, a stair detection and characterization pipeline is presented. The pipeline is tested on a differential drive robot using the ROS middleware, YOLOv4-tiny and a region growing based clustering algorithm. The pipeline’s staircase detector was implemented using the Neural Compute Engines (NCEs) of the OpenCV AI Kit with Depth (OAK-D) RGB-D camera, which allowed the implementation using the robot’s computer without a GPU and, thus, could be implemented in similar robots to increase autonomy. Furthermore, by using this pipeline we were able to implement a Fuzzy controller that allows the robot to align itself, autonomously, with the staircase. Our work can be used in different robots running the ROS middleware and can increase autonomy, allowing the operator to focus on the primary mission tasks. Furthermore, due to the design of the pipeline, it can be used with different types of RGB-D cameras, including those that generate noisy point clouds from low disparity depth images.

The Implementation of a Hierarchical Hybrid Navigation System for a Mobile Robotic Vehicle

<p>One of the challenges of robotics is to develop a robot control system capable of obtaining intelligent, suitable responses to dynamic environments. The basic requirements for accomplishing this is a robot control architecture and a hardware platform that can adapt the software and hardware to the current state of the environment. This has led researchers to design control architectures composed of distributed, independent and asynchronous behaviours. In line with this research, this thesis details the development of a control system which adopts a hierarchical hybrid navigation architecture designed at Victoria University of Wellington. The implementation of the control system is aimed towards one of Victoria University of Wellington’s fleet of mobile robotic platforms called MARVIN. MARVIN is a differential drive robot and the sensory equipment on the device includes infrared sensors and odometry. The control system has been implemented in C# .NET programming language adopting a Service- Oriented Architecture. This software framework provides several services along with a graphical user interface to configure the control system. Several experiments have been carried out to test the control system and the results indicate that the features of the navigation architecture have been accomplished</p>

The Implementation of a Hierarchical Hybrid Navigation System for a Mobile Robotic Vehicle

<p>One of the challenges of robotics is to develop a robot control system capable of obtaining intelligent, suitable responses to dynamic environments. The basic requirements for accomplishing this is a robot control architecture and a hardware platform that can adapt the software and hardware to the current state of the environment. This has led researchers to design control architectures composed of distributed, independent and asynchronous behaviours. In line with this research, this thesis details the development of a control system which adopts a hierarchical hybrid navigation architecture designed at Victoria University of Wellington. The implementation of the control system is aimed towards one of Victoria University of Wellington’s fleet of mobile robotic platforms called MARVIN. MARVIN is a differential drive robot and the sensory equipment on the device includes infrared sensors and odometry. The control system has been implemented in C# .NET programming language adopting a Service- Oriented Architecture. This software framework provides several services along with a graphical user interface to configure the control system. Several experiments have been carried out to test the control system and the results indicate that the features of the navigation architecture have been accomplished</p>

Implementation of a novel reactive navigation algorithm

In this project a reactive navigation algorithm is applied to a non-holonomic differential drive robot. The algorithm uses a stochastic process to navigate a robot through terrain while lacking a priori information. A graph is made from a random array of points that is used to connect the current location of the robot to its destination. Dijkstra's algorithm is used to select the shortest route that leads to the destination. The robot attempts to traverse this route until it detects that it is being blocked by an obstacle. The graph is then recreated with different random points, an a new route is calculated. This procedure is repeated until the robot arrives at its destination. This is tested by making a simulated robot with perfect localization travel through two kinds of environments. Processing speed is maintained by hashing location information according to its coordinates.

Implementation of a novel reactive navigation algorithm

In this project a reactive navigation algorithm is applied to a non-holonomic differential drive robot. The algorithm uses a stochastic process to navigate a robot through terrain while lacking a priori information. A graph is made from a random array of points that is used to connect the current location of the robot to its destination. Dijkstra's algorithm is used to select the shortest route that leads to the destination. The robot attempts to traverse this route until it detects that it is being blocked by an obstacle. The graph is then recreated with different random points, an a new route is calculated. This procedure is repeated until the robot arrives at its destination. This is tested by making a simulated robot with perfect localization travel through two kinds of environments. Processing speed is maintained by hashing location information according to its coordinates.

Minimum Energy Control of a Unicycle Model Robot

Point-to-point path planning for a kinematic model of a differential-drive wheeled mobile robot (WMR) with the goal of minimizing input energy is the focus of this work. An optimal control problem is formulated to determine the necessary conditions for optimality and the resulting two point boundary value problem is solved in closed form using Jacobi elliptic functions. The resulting nonlinear programming problem is solved for two variables and the results are compared to the traditional shooting method to illustrate that the Jacobi elliptic functions parameterize the exact profile of the optimal trajectory. A set of terminal constraints which lie on a circle in the first quadrant are used to generate a set of optimal solutions. It is noted that for maneuvers where the angle of the vector connecting the initial and terminal point is greater than a threshold, which is a function of the radius of the terminal constraint circle, the robot initially moves into the third quadrant before terminating in the first quadrant. The minimum energy solution is compared to two other optimal control formulations: (1) an extension of the Dubins vehicle model where the constant linear velocity of the robot is optimized for and (2) a simple turn and move solution, both of whose optimal paths lie entirely in the first quadrant. Experimental results are used to validate the optimal trajectories of the differential-drive robot.

Laser-Based People Detection and Obstacle Avoidance for a Hospital Transport Robot

This paper describes the development of a laser-based people detection and obstacle avoidance algorithm for a differential-drive robot, which is used for transporting materials along a reference path in hospital domains. Detecting humans from laser data is an important functionality for the safety of navigation in the shared workspace with people. Nevertheless, traditional methods normally utilize machine learning techniques on hand-crafted geometrical features extracted from individual clusters. Moreover, the datasets used to train the models are usually small and need to manually label every laser scan, increasing the difficulty and cost of deploying people detection algorithms in new environments. To tackle these problems, (1) we propose a novel deep learning-based method, which uses the deep neural network in a sliding window fashion to effectively classify every single point of a laser scan. (2) To increase the speed of inference without losing performance, we use a jump distance clustering method to decrease the number of points needed to be evaluated. (3) To reduce the workload of labeling data, we also propose an approach to automatically annotate datasets collected in real scenarios. In general, the proposed approach runs in real-time and performs much better than traditional methods. Secondly, conventional pure reactive obstacle avoidance algorithms can produce inefficient and oscillatory behaviors in dynamic environments, making pedestrians confused and possibly leading to dangerous reactions. To improve the legibility and naturalness of obstacle avoidance in human crowded environments, we introduce a sampling-based local path planner, similar to the method used in autonomous driving cars. The key idea is to avoid obstacles by switching lanes. We also adopt a simple rule to decrease the number of unnecessary deviations from the reference path. Experiments carried out in real-world environments confirmed the effectiveness of the proposed algorithms.