Design of a lightweight, modular robotic vehicle for the sustainable intensification of broadacre agriculture

This thesis presents the design process and the prototyping of a lightweight, modular robotic vehicle for the sustainable intensification of broadacre agriculture. Achieved by the joint operation of multiple autonomous vehicles to improve energy consumption, reduce labour, and increase efficiency in the application of inputs for the management of crops. The Small Robotic Farm Vehicle (SRFV) is a lightweight and energy efficient robotic vehicle with a configurable, modular design. It is capable of undertaking a range of agricultural tasks, including fertilising and weed management through mechanical intervention and precision spraying, whilst being more than an order of magnitude lower in weight than existing broadacre agricultural equipment.

Design and evaluation of decision and control strategies for autonomous vision-based see and avoid systems

This paper details the design and performance assessment of a unique collision avoidance decision and control strategy for autonomous vision-based See and Avoid systems. The general approach revolves around re-positioning a collision object in the image using image-based visual servoing, without estimating range or time to collision. The decision strategy thus involves determining where to move the collision object, to induce a safe avoidance manuever, and when to cease the avoidance behaviour. These tasks are accomplished by exploiting human navigation models, spiral motion properties, expected image feature uncertainty and the rules of the air. The result is a simple threshold based system that can be tuned and statistically evaluated by extending performance assessment techniques derived for alerting systems. Our results demonstrate how autonomous vision-only See and Avoid systems may be designed under realistic problem constraints, and then evaluated in a manner consistent to aviation expectations.

Robotic detection and tracking of Crown-Of-Thorns starfish

This paper presents a novel vision-based underwater robotic system for the identification and control of Crown-Of-Thorns starfish (COTS) in coral reef environments. COTS have been identified as one of the most significant threats to Australia's Great Barrier Reef. These starfish literally eat coral, impacting large areas of reef and the marine ecosystem that depends on it. Evidence has suggested that land-based nutrient runoff has accelerated recent outbreaks of COTS requiring extensive use of divers to manually inject biological agents into the starfish in an attempt to control population numbers. Facilitating this control program using robotics is the goal of our research. In this paper we introduce a vision-based COTS detection and tracking system based on a Random Forest Classifier (RFC) trained on images from underwater footage. To track COTS with a moving camera, we embed the RFC in a particle filter detector and tracker where the predicted class probability of the RFC is used as an observation probability to weight the particles, and we use a sparse optical flow estimation for the prediction step of the filter. The system is experimentally evaluated in a realistic laboratory setup using a robotic arm that moves a camera at different speeds and heights over a range of real-size images of COTS in a reef environment.

Improving monocular SLAM with altimeter hints for fixed-wing aircraft navigation and emergency landing

This paper presents a visual SLAM method for temporary satellite dropout navigation, here applied on fixed- wing aircraft. It is designed for flight altitudes beyond typical stereo ranges, but within the range of distance measurement sensors. The proposed visual SLAM method consists of a common localization step with monocular camera resectioning, and a mapping step which incorporates radar altimeter data for absolute scale estimation. With that, there will be no scale drift of the map and the estimated flight path. The method does not require simplifications like known landmarks and it is thus suitable for unknown and nearly arbitrary terrain. The method is tested with sensor datasets from a manned Cessna 172 aircraft. With 5% absolute scale error from radar measurements causing approximately 2-6% accumulation error over the flown distance, stable positioning is achieved over several minutes of flight time. The main limitations are flight altitudes above the radar range of 750 m where the monocular method will suffer from scale drift, and, depending on the flight speed, flights below 50 m where image processing gets difficult with a downwards-looking camera due to the high optical flow rates and the low image overlap.

Reasoning about natural language phrases for semantic goal driven exploration

This paper presents a symbolic navigation system that uses spatial language descriptions to inform goal-directed exploration in unfamiliar office environments. An abstract map is created from a collection of natural language phrases describing the spatial layout of the environment. The spatial representation in the abstract map is controlled by a constraint based interpretation of each natural language phrase. In goal-directed exploration of an unseen office environment, the robot links the information in the abstract map to observed symbolic information and its grounded world representation. This paper demonstrates the ability of the system, in both simulated and real-world trials, to efficiently find target rooms in environments that it has never been to previously. In three unexplored environments, it is shown that on average the system travels only 8.42% further than the optimal path when using only natural language phrases to complete navigation tasks.

Distributed Robotic Vision as a service

The vision sense of standalone robots is limited by line of sight and onboard camera capabilities, but processing video from remote cameras puts a high computational burden on robots. This paper describes the Distributed Robotic Vision Service, DRVS, which implements an on-demand distributed visual object detection service. Robots specify visual information requirements in terms of regions of interest and object detection algorithms. DRVS dynamically distributes the object detection computation to remote vision systems with processing capabilities, and the robots receive high-level object detection information. DRVS relieves robots of managing sensor discovery and reduces data transmission compared to image sharing models of distributed vision. Navigating a sensorless robot from remote vision systems is demonstrated in simulation as a proof of concept.

Autonomous UAVs wildlife detection using thermal imaging, predictive navigation and computer vision

There is an increased interest on the use of Unmanned Aerial Vehicles (UAVs) for wildlife and feral animal monitoring around the world. This paper describes a novel system which uses a predictive dynamic application that places the UAV ahead of a user, with a low cost thermal camera, a small onboard computer that identifies heat signatures of a target animal from a predetermined altitude and transmits that target’s GPS coordinates. A map is generated and various data sets and graphs are displayed using a GUI designed for easy use. The paper describes the hardware and software architecture and the probabilistic model for downward facing camera for the detection of an animal. Behavioral dynamics of target movement for the design of a Kalman filter and Markov model based prediction algorithm are used to place the UAV ahead of the user. Geometrical concepts and Haversine formula are applied to the maximum likelihood case in order to make a prediction regarding a future state of the user, thus delivering a new way point for autonomous navigation. Results show that the system is capable of autonomously locating animals from a predetermined height and generate a map showing the location of the animals ahead of the user.

Towards vision-based deep reinforcement learning for robotic motion control

This paper introduces a machine learning based system for controlling a robotic manipulator with visual perception only. The capability to autonomously learn robot controllers solely from raw-pixel images and without any prior knowledge of configuration is shown for the first time. We build upon the success of recent deep reinforcement learning and develop a system for learning target reaching with a three-joint robot manipulator using external visual observation. A Deep Q Network (DQN) was demonstrated to perform target reaching after training in simulation. Transferring the network to real hardware and real observation in a naive approach failed, but experiments show that the network works when replacing camera images with synthetic images.

A Distributed Robotic Vision Service

Robotic vision is limited by line of sight and onboard camera capabilities. Robots can acquire video or images from remote cameras, but processing additional data has a computational burden. This paper applies the Distributed Robotic Vision Service, DRVS, to robot path planning using data outside line-of-sight of the robot. DRVS implements a distributed visual object detection service to distributes the computation to remote camera nodes with processing capabilities. Robots request task-specific object detection from DRVS by specifying a geographic region of interest and object type. The remote camera nodes perform the visual processing and send the high-level object information to the robot. Additionally, DRVS relieves robots of sensor discovery by dynamically distributing object detection requests to remote camera nodes. Tested over two different indoor path planning tasks DRVS showed dramatic reduction in mobile robot compute load and wireless network utilization.

Uncertainty based online planning for UAV target finding in cluttered and GPS-denied environments

There are some scenarios in which Unmmaned Aerial Vehicle (UAV) navigation becomes a challenge due to the occlusion of GPS systems signal, the presence of obstacles and constraints in the space in which a UAV operates. An additional challenge is presented when a target whose location is unknown must be found within a confined space. In this paper we present a UAV navigation and target finding mission, modelled as a Partially Observable Markov Decision Process (POMDP) using a state-of-the-art online solver in a real scenario using a low cost commercial multi rotor UAV and a modular system architecture running under the Robotic Operative System (ROS). Using POMDP has several advantages to conventional approaches as they take into account uncertainties in sensor information. We present a framework for testing the mission with simulation tests and real flight tests in which we model the system dynamics and motion and perception uncertainties. The system uses a quad-copter aircraft with an board downwards looking camera without the need of GPS systems while avoiding obstacles within a confined area. Results indicate that the system has 100% success rate in simulation and 80% rate during flight test for finding targets located at different locations.

Autonomous greenhouse gas sampling using multiple robotic boats

Accurately quantifying total greenhouse gas emissions (e.g. methane) from natural systems such as lakes, reservoirs and wetlands requires the spatial-temporal measurement of both diffusive and ebullitive (bubbling) emissions. Traditional, manual, measurement techniques provide only limited localised assessment of methane flux, often introducing significant errors when extrapolated to the whole-of-system. In this paper, we directly address these current sampling limitations and present a novel multiple robotic boat system configured to measure the spatiotemporal release of methane to atmosphere across inland waterways. The system, consisting of multiple networked Autonomous Surface Vehicles (ASVs) and capable of persistent operation, enables scientists to remotely evaluate the performance of sampling and modelling algorithms for real-world process quantification over extended periods of time. This paper provides an overview of the multi-robot sampling system including the vehicle and gas sampling unit design. Experimental results are shown demonstrating the system’s ability to autonomously navigate and implement an exploratory sampling algorithm to measure methane emissions on two inland reservoirs.

A shallow water AUV for benthic and water column observations

Autonomous underwater vehicles (AUVs) are becoming commonplace in the study of inshore coastal marine habitats. Combined with shipboard systems, scientists are able to make in-situ measurements of water column and benthic properties. In CSIRO, autonomous gliders are used to collect water column data, while surface vessels are used to collect bathymetry information through the use of swath mapping, bottom grabs, and towed video systems. Although these methods have provided good data coverage for coastal and deep waters beyond 50m, there has been an increasing need for autonomous in-situ sampling in waters less than 50m deep. In addition, the collection of benthic and water column data has been conducted separately, requiring extensive post-processing to combine data streams. As such, a new AUV was developed for in-situ observations of both benthic habitat and water column properties in shallow waters. This paper provides an overview of the Starbug X AUV system, its operational characteristics including vision-based navigation and oceanographic sensor integration.

Capturability of realistic generalized true proportional navigation

The capturability of a realistic generalized true proportional navigation (RGTPN) guidance law, against a nonmaneuvering target, is analyzed. The RGTPN law is obtained by relaxing the somewhat unrealistic assumption of constant closing velocity, made in all earlier studies on generalized true proportional navigation (GTPN), and incorporating the actual time-varying value in the guidance law. Closed-form solutions for the complete capture region of RGTPN is obtained in terms of both zero and acceptable non-zero miss distances. It is shown that the capture region of RGTPN in the initial relative velocity space is significantly smaller than that of GTPN, for reasonable values of navigation constant (N) and angular direction (eta) of the missile commanded latax. However, for certain values of N and eta, capturability of RGTPN is found to be better. It is also shown that if in one of the versions of GTPN, which uses constant values of both the closing velocity and the line-of-sight (LOS) angular velocity in the guidance law, the corresponding realistic time-varying quantities are used, the capture region actually expands to cover the whole of the initial relative velocity space. A number of examples are given to compare the capture performance of RGTPN with other versions of the GTPN guidance laws.

Proportional navigation with delayed line-of-sight rate

This brief discusses the convergence analysis of proportional navigation (PN) guidance law in the presence of delayed line-of-sight (LOS) rate information. The delay in the LOS rate is introduced by the missile guidance system that uses a low cost sensor to obtain LOS rate information by image processing techniques. A Lyapunov-like function is used to analyze the convergence of the delay differential equation (DDE) governing the evolution of the LOS rate. The time-to-go until which decreasing behaviour of the Lyapunov-like function can be guaranteed is obtained. Conditions on the delay for finite time convergence of the LOS rate are presented for the linearized engagement equation. It is observed that in the presence of line-of-sight rate delay, increasing the effective navigation constant of the PN guidance law deteriorates its performance. Numerical simulations are presented to validate the results.

Broadcast Control Mechanism for Positional Consensus in Multiagent Systems

In this paper, a strategy for controlling a group of agents to achieve positional consensus is presented. The problem is constrained by the requirement that every agent must be given the same control input through a broadcast communication mechanism. Although the control command is computed using state information in a global framework, the control input is implemented by the agents in a local coordinate frame. We propose a novel linear programming (LP) formulation that is computationally less intensive than earlier proposed methods. Moreover, a random perturbation input in the control command that helps the agents to come close to each other even for a large number of agents, which was not possible with an existing strategy in the literature, is introduced. The method is extended to achieve positional consensus at a prespecified location. The effectiveness of the approach is illustrated through simulation results. A comparison between the LP approach and the existing second-order cone programming-based approach is also presented. The algorithm was successfully implemented on a robotic platform with three robots.