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.

Enhancing human action recognition with region proposals

Deep convolutional network models have dominated recent work in human action recognition as well as image classification. However, these methods are often unduly influenced by the image background, learning and exploiting the presence of cues in typical computer vision datasets. For unbiased robotics applications, the degree of variation and novelty in action backgrounds is far greater than in computer vision datasets. To address this challenge, we propose an “action region proposal” method that, informed by optical flow, extracts image regions likely to contain actions for input into the network both during training and testing. In a range of experiments, we demonstrate that manually segmenting the background is not enough; but through active action region proposals during training and testing, state-of-the-art or better performance can be achieved on individual spatial and temporal video components. Finally, we show by focusing attention through action region proposals, we can further improve upon the existing state-of-the-art in spatio-temporally fused action recognition performance.

A novel approach to 6-DOF adaptive trajectory tracking control of an AUV in the presence of parameter uncertainties

In this paper, the trajectory tracking control of an autonomous underwater vehicle (AUVs) in six-degrees-of-freedom (6-DOFs) is addressed. It is assumed that the system parameters are unknown and the vehicle is underactuated. An adaptive controller is proposed, based on Lyapunov׳s direct method and the back-stepping technique, which interestingly guarantees robustness against parameter uncertainties. The desired trajectory can be any sufficiently smooth bounded curve parameterized by time even if consist of straight line. In contrast with the majority of research in this field, the likelihood of actuators׳ saturation is considered and another adaptive controller is designed to overcome this problem, in which control signals are bounded using saturation functions. The nonlinear adaptive control scheme yields asymptotic convergence of the vehicle to the reference trajectory, in the presence of parametric uncertainties. The stability of the presented control laws is proved in the sense of Lyapunov theory and Barbalat׳s lemma. Efficiency of presented controller using saturation functions is verified through comparing numerical simulations of both controllers.

A bottom-up integration of vision and actions to create cognitive humanoids

In recent years more and more complex humanoid robots have been developed. On the other hand programming these systems has become more difficult. There is a clear need for such robots to be able to adapt and perform certain tasks autonomously, or even learn by themselves how to act. An important issue to tackle is the closing of the sensorimotor loop. Especially when talking about humanoids the tight integration of perception with actions will allow for improved behaviours, embedding adaptation on the lower-level of the system.

Automatic Lameness Detection in a Milking Robot : Instrumentation, measurement software, algorithms for data analysis and a neural network model

The aim of this thesis is to develop a fully automatic lameness detection system that operates in a milking robot. The instrumentation, measurement software, algorithms for data analysis and a neural network model for lameness detection were developed. Automatic milking has become a common practice in dairy husbandry, and in the year 2006 about 4000 farms worldwide used over 6000 milking robots. There is a worldwide movement with the objective of fully automating every process from feeding to milking. Increase in automation is a consequence of increasing farm sizes, the demand for more efficient production and the growth of labour costs. As the level of automation increases, the time that the cattle keeper uses for monitoring animals often decreases. This has created a need for systems for automatically monitoring the health of farm animals. The popularity of milking robots also offers a new and unique possibility to monitor animals in a single confined space up to four times daily. Lameness is a crucial welfare issue in the modern dairy industry. Limb disorders cause serious welfare, health and economic problems especially in loose housing of cattle. Lameness causes losses in milk production and leads to early culling of animals. These costs could be reduced with early identification and treatment. At present, only a few methods for automatically detecting lameness have been developed, and the most common methods used for lameness detection and assessment are various visual locomotion scoring systems. The problem with locomotion scoring is that it needs experience to be conducted properly, it is labour intensive as an on-farm method and the results are subjective. A four balance system for measuring the leg load distribution of dairy cows during milking in order to detect lameness was developed and set up in the University of Helsinki Research farm Suitia. The leg weights of 73 cows were successfully recorded during almost 10,000 robotic milkings over a period of 5 months. The cows were locomotion scored weekly, and the lame cows were inspected clinically for hoof lesions. Unsuccessful measurements, caused by cows standing outside the balances, were removed from the data with a special algorithm, and the mean leg loads and the number of kicks during milking was calculated. In order to develop an expert system to automatically detect lameness cases, a model was needed. A probabilistic neural network (PNN) classifier model was chosen for the task. The data was divided in two parts and 5,074 measurements from 37 cows were used to train the model. The operation of the model was evaluated for its ability to detect lameness in the validating dataset, which had 4,868 measurements from 36 cows. The model was able to classify 96% of the measurements correctly as sound or lame cows, and 100% of the lameness cases in the validation data were identified. The number of measurements causing false alarms was 1.1%. The developed model has the potential to be used for on-farm decision support and can be used in a real-time lameness monitoring system.

MPC controlled multirotor with suspended slung load: System architecture and visual load detection

There is an increased interest in the use of Unmanned Aerial Vehicles for load transportation from environmental remote sensing to construction and parcel delivery. One of the main challenges is accurate control of the load position and trajectory. This paper presents an assessment of real flight trials for the control of an autonomous multi-rotor with a suspended slung load using only visual feedback to determine the load position. This method uses an onboard camera to take advantage of a common visual marker detection algorithm to robustly detect the load location. The load position is calculated using an onboard processor, and transmitted over a wireless network to a ground station integrating MATLAB/SIMULINK and Robotic Operating System (ROS) and a Model Predictive Controller (MPC) to control both the load and the UAV. To evaluate the system performance, the position of the load determined by the visual detection system in real flight is compared with data received by a motion tracking system. The multi-rotor position tracking performance is also analyzed by conducting flight trials using perfect load position data and data obtained only from the visual system. Results show very accurate estimation of the load position (~5% Offset) using only the visual system and demonstrate that the need for an external motion tracking system is not needed for this task.

Find my office: Navigating real space from semantic descriptions

This paper shows that by using only symbolic language phrases, a mobile robot can purposefully navigate to specified rooms in previously unexplored environments. The robot intelligently organises a symbolic language description of the unseen environment and “imagines” a representative map, called the abstract map. The abstract map is an internal representation of the topological structure and spatial layout of symbolically defined locations. To perform goal-directed exploration, the abstract map creates a high-level semantic plan to reason about spaces beyond the robot’s known world. While completing the plan, the robot uses the metric guidance provided by a spatial layout, and grounded observations of door labels, to efficiently guide its navigation. The system is shown to complete exploration in unexplored spaces by travelling only 13.3% further than the optimal path.

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.

Status on pre-surgical deformation apparatus for fracture fixation plates

Purpose: This paper reviews the apparatus used for deformation of bone fracture fixation plates during orthopaedic surgeries including surgical irons, pliers and bending press tools. This paper extends the review to various machineries in non-medical industries and adopts their suitability to clinics-related applications and also covers the evolution of orthopaedic bone plates. This review confirms that none of the studied machineries can be implemented for the deformation of bone fracture fixation plates during orthopaedic surgeries. In addition, this paper also presents the novel apparatus that are designed from scratch for this specific purpose. Several conceptual designs have been proposed and evaluated recently. It has been found that Computer Numerical Control (CNC) systems are not the golden solution to this problem and one needs to attempt to design the robotic arm system. A new design of robotic arm that can be used for facilitating orthopaedic surgeries is being completed.

Visual detection of occluded crop: For automated harvesting

This paper presents a novel crop detection system applied to the challenging task of field sweet pepper (capsicum) detection. The field-grown sweet pepper crop presents several challenges for robotic systems such as the high degree of occlusion and the fact that the crop can have a similar colour to the background (green on green). To overcome these issues, we propose a two-stage system that performs per-pixel segmentation followed by region detection. The output of the segmentation is used to search for highly probable regions and declares these to be sweet pepper. We propose the novel use of the local binary pattern (LBP) to perform crop segmentation. This feature improves the accuracy of crop segmentation from an AUC of 0.10, for previously proposed features, to 0.56. Using the LBP feature as the basis for our two-stage algorithm, we are able to detect 69.2% of field grown sweet peppers in three sites. This is an impressive result given that the average detection accuracy of people viewing the same colour imagery is 66.8%.

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.

Decision fusion for reliable flood mapping using remote sensing images

Flood extent mapping is a basic tool for flood damage assessment, which can be done by digital classification techniques using satellite imageries, including the data recorded by radar and optical sensors. However, converting the data into the information we need is not a straightforward task. One of the great challenges involved in the data interpretation is to separate the permanent water bodies and flooding regions, including both the fully inundated areas and the wet areas where trees and houses are partly covered with water. This paper adopts the decision fusion technique to combine the mapping results from radar data and the NDVI data derived from optical data. An improved capacity in terms of identifying the permanent or semi-permanent water bodies from flood inundated areas has been achieved. Computer software tools Multispec and Matlab were used.

Evaluation of Moderate-Resolution Imaging Spectroradiometer (MODIS) collection 004 (C004) aerosol retrievals at Kanpur, Indo-Gangetic basin

[1] We have compared the spectral aerosol optical depth (AOD, tau lambda) and aerosol fine mode fraction (AFMF) of Collection 004 (C004) derived from Moderate-Resolution Imaging Spectroradiometer (MODIS) on board National Aeronautics and Space Administration's (NASA) Terra and Aqua platforms with that obtained from Aerosol Robotic Network (AERONET) at Kanpur (26.45 degrees N, 80.35 degrees E), India for the period 2001-2005. The spatially-averaged (0.5 degrees x 0.5 degrees centered at AERONET sunphotometer) MODIS Level-2 aerosol parameters (10 km at nadir) were compared with the temporally averaged AERONET-measured AOD (within +/- 30 minutes of MODIS overpass). We found that MODIS systematically overestimated AOD during the pre-monsoon season (March to June, known to be influenced by dust aerosols). The errors in AOD at 0.66 mu m were correlated with the apparent reflectance at 2.1 mu m (rho*(2.1)) which MODIS C004 uses to estimate the surface reflectance in the visible channels (rho(0.47) = rho*(2.1)/ 4, rho(0.66) = rho*(2.1)/ 2). The large errors in AOD (Delta tau(0.66) > 0.3) are found to be associated with the higher values of rho*(2.1) (0.18 to 0.25), where the uncertainty in the ratios of reflectance is large (Delta rho(0.66) +/- 0.04, Delta rho(0.47) +/- 0.02). This could have resulted in lower surface reflectance, higher aerosol path radiance and thus lead to overestimation in AOD. While MODIS-derived AFMF has binary distribution (1 or 0) with too low (AFMF < 0.2) during dust-loading period, and similar to 1 for the rest of the retrievals, AERONET showed range of values (0.4 to 0.9). The errors in tau(0.66) were also high in the scattering angle range 110 degrees - 140 degrees, where the optical effects of nonspherical dust particles are different from that of spherical particles.

Revocation and update of trust in autonomous delay tolerant networks

A Delay Tolerant Network (DTN) is a dynamic, fragmented, and ephemeral network formed by a large number of highly mobile nodes. DTNs are ephemeral networks with highly mobile autonomous nodes. This requires distributed and self-organised approaches to trust management. Revocation and replacement of security credentials under adversarial influence by preserving the trust on the entity is still an open problem. Existing methods are mostly limited to detection and removal of malicious nodes. This paper makes use of the mobility property to provide a distributed, self-organising, and scalable revocation and replacement scheme. The proposed scheme effectively utilises the Leverage of Common Friends (LCF) trust system concepts to revoke compromised security credentials, replace them with new ones, whilst preserving the trust on them. The level of achieved entity confidence is thereby preserved. Security and performance of the proposed scheme is evaluated using an experimental data set in comparison with other schemes based around the LCF concept. Our extensive experimental results show that the proposed scheme distributes replacement credentials up to 35% faster and spreads spoofed credentials of strong collaborating adversaries up to 50% slower without causing any significant increase on the communication and storage overheads, when compared to other LCF based schemes.

Extending visual perception with haptic exploration for improved scene understanding

Scene understanding has been investigated from a mainly visual information point of view. Recently depth has been provided an extra wealth of information, allowing more geometric knowledge to fuse into scene understanding. Yet to form a holistic view, especially in robotic applications, one can create even more data by interacting with the world. In fact humans, when growing up, seem to heavily investigate the world around them by haptic exploration. We show an application of haptic exploration on a humanoid robot in cooperation with a learning method for object segmentation. The actions performed consecutively improve the segmentation of objects in the scene.