Patrick Benavidez

Mobile robot navigation and target tracking system

This paper presents the framework for the navigation and target tracking system for a mobile robot. Navigation and target tracking are to be performed using a Microsoft Xbox Kinect sensor which provides RGB color and 3D depth imaging data to an x86 based computer onboard the robot running Ubuntu Linux. A fuzzy logic controller to be implemented on the computer is considered for control of the robot in obstacle avoidance and target following. Data collected by the computer is to be sent to a server for processing with learning-based systems utilizing neural networks for pattern recognition, object tracking, long-term path planning and process improvement. An eventual goal of this work is to create a multi-agent robot system that is able to work autonomously in an outdoor environment.

Decentralized Motion Coordination for a Formation of Rovers

In this paper, a decentralized formation control is proposed which enables collision free coordination and navigation of agents. We present a simple method to define the formation of multi-agents and individual identities (IDs) of agents. Two decentralized coordination and navigation techniques are proposed for the formation of rovers. Agents decide their own behaviors onboard depending upon the motion initiative of the master agent of the formation. In these approaches, any agent can estimate behavior of other agents in the formation. These will reduce the dependency of individual agent on other agents while taking decisions. These approaches reduce the communication burden on the formation where only the master agent broadcasts its motion status per sampled time. Any front agent can act as a master agent without affecting the formation in case of fault in initial master agent. The main idea of this paper is to develop an adequate computational model under which agents in the formation will perform to coordinate among each other. Assignments of IDs to agents are very useful in real-time applications. These proposed schemes are suitable for obstacle avoidance in unknown environment as a whole formation. Agents are free from collision among each other during navigation. These schemes can be used for velocity as well as orientation alignment problems for a multi-agent rover network. These schemes are tested with extensive simulations and responses of agents show satisfactory performances to deal with different environmental conditions.

Multi-domain robotic swarm communication system

As swarm of robots from different domains works together in a system of systems, the need arises for inter-swarm communication. This paper presents a viable solution for robotic swarm communication and navigation for different autonomous applications. Communication is achieved through ZigBee radio modems and an expandable protocol to accommodate different types of data. This proposed communication system also allows dynamic swarm expansion, where a new member can be added to the swarm family. It is a complementary approach for task coordination and navigation. Navigation is an important issue to accomplish the coordination of tasks in a swarm of robots. Different environmental issues, related to navigation, have been discussed and are presented through simulation results and the real-time communication test is presented through the experimental result.

Cloud-based realtime robotic Visual SLAM

Prior work has shown that Visual SLAM (VSLAM) algorithms can successfully be used for realtime processing on local robots. As the data processing requirements increase, due to image size or robot velocity constraints, local processing may no longer be practical. Offloading the VSLAM processing to systems running in a cloud deployment of Robot Operating System (ROS) is proposed as a method for managing increasing processing constraints. The traditional bottleneck with VSLAM performing feature identification and matching across a large database. In this paper, we present a system and algorithms to reduce computational time and storage requirements for feature identification and matching components of VSLAM by offloading the processing to a cloud comprised of a cluster of compute nodes. We compare this new approach to our prior approach where only the local resources of the robot were used, and examine the increase in throughput made possible with this new processing architecture.

Landing of an Ardrone 2.0 quadcopter on a mobile base using fuzzy logic

In this paper, a fuzzy control system is presented for an unmanned aerial vehicle (UAV) which provides aerial support for an unmanned ground vehicle (UGV). The UGV acts as a mobile launching pad for the UAV. The UAV provides additional environmental image feedback to the UGV. Our UAV of choice is a Parrot ArDrone 2.0 quadcopter, a small four rotored aerial vehicle, competent for its agile flight and video feedback capabilities. This paper presents design and simulation of fuzzy logic controllers for performing landing and altitude control. Image processing and Mamdani-type inference are used for converting sensor input into control signals used to control the UAV.

Improving visual SLAM algorithms for use in realtime robotic applications

Many vision-based Simultaneous Localization And Mapping (vSLAM) algorithms require large amounts of computational power and storage. With these requirements, vSLAM is difficult to implement in real time. One known bottleneck in vSLAM is performing feature identification and matching across a large database. In this paper, we present a system and algorithms to reduce computational time and storage requirements for feature identification and matching components of vSLAM. We compare our algorithms using ORB and SURF to their unmodified versions readily available datasets and show significant reductions in storage requirements and calculation time.

Landing of a quadcopter on a mobile base using fuzzy logic

In this paper, we present control systems for an unmanned aerial vehicle (UAV) which provides aerial support for an unmanned ground vehicle (UGV). The UGV acts as a mobile launching pad for the UAV. The UAV provides additional environmental image feedback to the UGV. Our UAV of choice is a Parrot ArDrone 2.0 quadcopter, a small four rotored aerial vehicle, picked for its agile flight and video feedback capabilities. This paper presents design and simulation of fuzzy logic controllers for performing landing, hovering, and altitude control. Image processing and Mamdani-type inference are used for converting sensor input into control signals used to control the UAV.

Formation control implementation using Kobuki TurtleBots and Parrot Bebop drone

Formation control of a collection of vehicles is a topic that has generated a lot of interest in the research community. This interest primarily stems from the increased performance and robustness that is provided by a swarm of agents as compared to an individual member. Formation control can be achieved through many approaches. The approach used by this paper is based on a leader-follower premise. A network of agents can be controlled by assigning a leader for each agent in the formation. The group as a whole will be capable of following either a Virtual Leader (VL) or an agent within the group. The algorithm applied to a test-bed consisting of three Kobuki TurtleBot2 robots. Each Turtlebot2 is programmed to follow a pre-defined virtual point in the formation. The test space is monitored by a Parrot Bebop drone hovering overhead that identifies agents uniquely through image processing techniques. The agents can then move in the test space, based on the leaders position, while maintaining a formation.

Design of a home multi-robot system for the elderly and disabled

Home-based assistive robotic care for the elderly and disabled has long been a goal of robotics researchers. Unfortunately, no single group has solved the problem of making robots that will perform a set of tasks sufficient enough to warrant the cost to the end consumer. Numerous advances and improvements in computing, communication and related robotic technologies have been paving the way towards cheaper, more capable robots. We propose a home robot system consisting of a set of heterogeneous robots with different task spaces, cloud computing to enhance the abilities of the system, integration with existing home infrastructure, and compatibility with mobile technology. A high level of integration with the open source software of the Robot Operating System (ROS) is proposed to accelerate the design process. For the exact types of robots, we propose to use an enhanced floor cleaning robot and a mobility and vision assistance robot in the form of an improved rollator walker.

A deep vision landmark framework for robot navigation

Robot navigation requires specific techniques for guiding a mobile robot to a desired destination. In general, a desired path is required in an environment described by different terrain and a set of distinct objects, such as obstacles and particular landmarks. In this paper, a new approach for autonomous navigation is presented using machine learning techniques such as Convolutional Neural Network to identify markers or objects from images and Robot Operating System and Object Position Discovery system to orient to the marker, calculate the distance and navigate towards these markers using depth camera.