As consensus across the various published AI ethics principles is approached, a gap remains between high-level principles and practical techniques that can be readily adopted to design and develop responsible AI systems. We examine the practices and experiences of researchers and engineers from Australia’s national scientific research agency (CSIRO), who are involved in designing and developing AI systems for many application areas. Semi-structured interviews were used to examine how the practices of the participants relate to and align with a set of high-level AI ethics principles proposed by the Australian Government. The principles comprise: (1) privacy protection and security, (2) reliability and safety, (3) transparency and explainability, (4) fairness, (5) contestability, (6) accountability, (7) human-centred values, (8) human, social and environmental well-being. Discussions on the gained insights from the interviews include various tensions and trade-offs between the principles, and provide suggestions for implementing each high-level principle. We also present suggestions aiming to enhance associated support mechanisms.

Response efforts in emergency applications such as border protection, humanitarian relief and disaster monitoring have improved with the use of Unmanned Aerial Vehicles (UAVs), which provide a flexibly deployed eye in the sky. These efforts have been further improved with advances in autonomous behaviours such as obstacle avoidance, take-off, landing, hovering and waypoint flight modes. However, most UAVs lack autonomous decision making for navigating in complex environments. This limitation creates a reliance on ground control stations to UAVs and, therefore, on their communication systems. The challenge is even more complex in indoor flight operations, where the strength of the Global Navigation Satellite System (GNSS) signals is absent or weak and compromises aircraft behaviour. This paper proposes a UAV framework for autonomous navigation to address uncertainty and partial observability from imperfect sensor readings in cluttered indoor scenarios. The framework design allocates the computing processes onboard the flight controller and companion computer of the UAV, allowing it to explore dangerous indoor areas without the supervision and physical presence of the human operator. The system is illustrated under a Search and Rescue (SAR) scenario to detect and locate victims inside a simulated office building. The navigation problem is modelled as a Partially Observable Markov Decision Process (POMDP) and solved in real time through the Augmented Belief Trees (ABT) algorithm. Data is collected using Hardware in the Loop (HIL) simulations and real flight tests. Experimental results show the robustness of the proposed framework to detect victims at various levels of location uncertainty. The proposed system ensures personal safety by letting the UAV to explore dangerous environments without the intervention of the human operator.

Recent advances in autonomy of unmanned aerial vehicles (UAVs) have increased their use in remote sensing applications, such as precision agriculture, biosecurity, disaster monitoring, and surveillance. However, onboard UAV cognition capabilities for understanding and interacting in environments with imprecise or partial observations, for objects of interest within complex scenes, are limited, and have not yet been fully investigated. This limitation of onboard decision-making under uncertainty has delegated the motion planning strategy in complex environments to human pilots, which rely on communication subsystems and real-time telemetry from ground control stations. This paper presents a UAV-based autonomous motion planning and object finding system under uncertainty and partial observability in outdoor environments. The proposed system architecture follows a modular design, which allocates most of the computationally intensive tasks to a companion computer onboard the UAV to achieve high-fidelity results in simulated environments. We demonstrate the system with a search and rescue (SAR) case study, where a lost person (victim) in bushland needs to be found using a sub-2 kg quadrotor UAV. The navigation problem is mathematically formulated as a partially observable Markov decision process (POMDP). A motion strategy (or policy) is obtained once a POMDP is solved mid-flight and in real time using augmented belief trees (ABT) and the TAPIR toolkit. The system’s performance was assessed using three flight modes: (1) mission mode, which follows a survey plan and used here as the baseline motion planner; (2) offboard mode, which runs the POMDP-based planner across the flying area; and (3) hybrid mode, which combines mission and offboard modes for improved coverage in outdoor scenarios. Results suggest the increased cognitive power added by the proposed motion planner and flight modes allow UAVs to collect more accurate victim coordinates compared to the baseline planner. Adding the proposed system to UAVs results in improved robustness against potential false positive readings of detected objects caused by data noise, inaccurate detections, and elevated complexity to navigate in time-critical applications, such as SAR.

For over 15 years, the mlpack machine learning library has served as a "swiss army knife'' for C++-based machine learning (Curtin et al., 2013). Its efficient implementations of common and cutting-edge machine learning algorithms have been used in a wide variety of scientific and industrial applications. This paper overviews mlpack 4, a significant upgrade over its predecessor (Curtin et al., 2018). The library has been significantly refactored and redesigned to facilitate an easier prototyping-to-deployment pipeline, including bindings to other languages (Python, Julia, R, Go, and the command line) that allow prototyping to be seamlessly performed in environments other than C++.