Model-based reinforcement learning (RL) algorithms do not typically consider environments with multiple dynamic modes, where it is beneficial to avoid inoperable or undesirable modes. We present a model-based RL algorithm that constrains training to a single dynamic mode with high probability. This is a difficult problem because the mode constraint is a hidden variable associated with the environment’s dynamics. As such, it is 1) unknown a priori and 2) we do not observe its output from the environment, so cannot learn it with supervised learning. We present a nonparametric dynamic model which learns the mode constraint alongside the dynamic modes. Importantly, it learns latent structure that our planning scheme leverages to 1) enforce the mode constraint with high probability, and 2) escape local optima induced by the mode constraint. We validate our method by showing that it can solve a simulated quadcopter navigation task whilst providing a level of constraint satisfaction both during and after training.

Graceful degradation is a potential advantage of Multi-Robot Systems over Single-Robot Systems. In aerial robotics applications, such as infrastructure inspection, this trait is desirable as it would improve mission reliability despite the use of failure-prone low-cost drones. The Reliability-Aware Multi-Agent Coverage Path Planning (RA-MCPP) problem finds path plans for each robot to maximise the probability of mission completion by a given deadline. This paper proposes a path planner for RA-MCPP formulated in continuous time, enabling more complex realistic environments to be considered. The proposed method (i) extends a reliability evaluation framework to evaluate the Probability of Completion metric on asynchronous strategies on non-unit lattice graph environments, and (ii) introduces a greedy-genetic meta-heuristic optimisation method as a scalable and accurate RA-MCPP solver. This method is shown to provide plans with higher reliability when compared with existing approaches in three real inspection scenarios.

This paper presents a two-stage method to perform trajectory optimisation in multimodal dynamical systems with unknown nonlinear stochastic transition dynamics. The method finds trajectories that remain in a preferred dynamics mode where possible and in regions of the transition dynamics model that have been observed and can be predicted confidently. The first stage leverages a Mixture of Gaussian Process Experts method to learn a predictive dynamics model from historical data. Importantly, this model learns a gating function that indicates the probability of being in a particular dynamics mode at a given state location. This gating function acts as a coordinate map for a latent Riemannian manifold on which shortest trajectories are solutions to our trajectory optimisation problem. Based on this intuition, the second stage formulates a geometric cost function, which it then implicitly minimises by projecting the trajectory optimisation onto the second-order geodesic ODE; a classic result of Riemannian geometry. A set of collocation constraints are derived that ensure trajectories are solutions to this ODE, implicitly solving the trajectory optimisation problem.

A new strategy is proposed for scheduling Visual Odometry (VO) measurements for wheeled ground vehicles. Rather than having a fixed interval or distance between image acquisitions, we propose to trigger VO based on covariances from an Adaptive Extended Kalman Filter. The adopted model uses process noise to drive wheel slip estimation, which, when correctly identified, can be used with Wheel Odometry to provide frequent position estimates. When more dynamic terrain is detected, more VO measurements are scheduled to maintain localization accuracy. On the other hand, when the terrain is stable, VO usage is limited. The system is validated in a simple one-dimensional case using data captured during field trials using a representative rover. The results are promising as trajectories that were subjected to large errors are corrected.

This work considers the problem of generating computationally efficient quadrotor motion primitives between a given pose (position, velocity, and acceleration) and a goal plane in the presence of obstacles. A new motion primitive tool based on the logistic curve is proposed and a closed-form analytic approach is developed to satisfy constraints on starting pose, goal plane, velocity, acceleration, and jerk. The geometric obstacle avoidance problem is represented as a combinatorial set problem and a heuristic approach is proposed to accelerate the solution search. Numerical examples are presented to highlight the fast motion primitive generation in multi-obstacle pose-to-plane scenarios.

Supervisory constraints are developed for a trajectory optimizer for air traffic. By choosing to apply combinations of these constraints, a human controller can exercise intuitive influence over how conflicts between aircraft are resolved. This offers a compromise between the flexibility of an automated optimizer and the insight of a human controller. Requirements, such as the sense of resolution,-i.e., which aircraft goes first or over-are encoded as constraints on a mixed-integer linear program. Examples verify that the constraints work as expected and that the computation times required are reasonable.

Autonomous robots must operate in complex and changing environments subject to requirements on their behaviour. Verifying absolute satisfaction (true or false) of these requirements is challenging. Instead, we analyse requirements that admit flexible degrees of satisfaction. We analyse vague requirements using fuzzy logic, and probabilistic requirements using model checking. The resulting analysis method provides a partial ordering of system designs, identifying trade-offs between different requirements in terms of the degrees to which they are satisfied. A case study involving a home care robot interacting with a human is used to demonstrate the approach.

A method for real-time robot navigation with obstacle avoidance is presented. A two-stage approach is proposed: the use of online Simulated Annealing (SA) to optimize a convex operating region in configuration space is paired with Model Predictive Control (MPC) to determine a locally optimal motion plan. The method retains recursive feasibility guarantees from MPC and speed of solution of the convex optimal control problem. Meanwhile, the convexification performed by the SA enables the method to operate with unstructured environment representations, such as point clouds or line scans.

This paper presents a method of occluding depth edge-detection targeted towards RGB-D video streams and explores the use of these and other edge features in RGB-D SLAM. The proposed depth edge-detection approach uses prior information obtained from the previous RGB-D video frame to determine which areas of the current depth image are likely to contain edges due to image similarity. By limiting the search for edges to these areas a significant amount of computation time is saved compared to searching the entire image. Pixels belonging to both the depth and colour edges of an RGB-D image can be back projected using the depth component to form 3D point clouds of edge points. Registration between such edge point clouds is achieved using ICP and we present a realtime RGB-D SLAM system utilizing such back projected edge features. Experimental results are presented demonstrating the performance of both the proposed depth edge-detection and SLAM system using publicly available datasets.

The idea of a Cloned Controller to approximate optimised control algorithms in a real-time environment is introduced. A Cloned Controller is demonstrated using Linguistic Decision Trees (LDTs) to clone a Model Predictive Controller (MPC) based on Mixed Integer Linear Programming (MILP) for Unmanned Aerial Vehicle (UAV) path planning through a hostile environment. Modifications to the LDT algorithm are proposed to account for attributes with circular domains, such as bearings, and discontinuous output functions. The cloned controller is shown to produce near optimal paths whilst significantly reducing the decision period. Further investigation shows that the cloned controller generalises to the multi-obstacle case although this can lead to situations far outside of the training dataset and consequently result in decisions with a high level of uncertainty. A modification to the algorithm to improve the performance in regions of high uncertainty is proposed and shown to further enhance generalisation. The resulting controller combines the high performance of MPC–MILP with the rapid response of an LDT while providing a degree of transparency/interpretability of the decision making.

This paper characterises the power consumption of electric rotorcraft and derives an endurance estimation model for such aircraft powered by LiPo batteries. Theoretical analysis is backed by experimental flight tests using a popular commercial quadrotor. Experiments on Commercial Off-The-Shelf Lithium-Polymer batteries, which are the technology dominating the multi-rotor Unmanned Aerial Vehicle market, are carried out to determine battery run-time and specific energy/capacity models, whilst investigating the battery variability. These battery models are combined with the rotorcraft power model to provide an endurance estimation model, accounting for both battery variability as well as the electric propulsion system effects, which is experimentally validated through flight tests.

This paper describes an algorithm for robotic motion planning that is capable of optimising several cost functions simultaneously to provide optimised, feasible and collision-free paths. The algorithm is based on the best-first graph search algorithm using a Pareto frontier to evaluate costs at each node. Additionally, we include a calculation of the distribution of robot trajectories when the path is realised using a LQR based controller. This ensures that the possibility of collisions is greatly reduced. Results are provided that show multi-cost robotic path planning under position uncertainty and control constraints whilst simultaneously optimising distance travelled and fuel spent.

This paper describes a mixed-integer linear programming optimization method for the coupled problems of airport taxiway routing and runway scheduling. The receding-horizon formulation and the use of iteration in the avoidance constraints allows the scalability of the baseline algorithm presented, with examples based on Heathrow Airport, London, U.K., which contains up to 240 aircraft. The results show that average taxi times can be reduced by half, compared with the first-come-first-served approach. The main advantage is shown with the departure aircraft flow. Comparative testing demonstrates that iteration reduces the computational demand of the required separation constraints while introducing no loss in performance.

This paper presents a novel approach to navigation in an a priori unknown, GPS-denied environment. The aim is to combine dynamic path planning with the ability to learn about the environment. The vehicle is tasked with autonomous travel from an uncertain initial position to an uncertain target, without prior mapping information. The environment is modelled using linear segments that represent boundaries between the estimated traversable and non-traversable regions. The approach integrates Receding Horizon Control (RHC) and Simultaneous Localisation and Mapping (SLAM). The control problem is formulated as a mixed integer linear program (MILP) and explicitly includes the obstacles and vehicle dynamics. We present the results of our experiments using Pioneer robots, as well as, simulation results which clearly demonstrated the impact of each component of the system.

This paper develops and tests a novel rapid updating technique for use with a nonlinear branch and bound optimisation method, tailored for finding optimal trajectories for a vehicle constrained to avoid fixed obstacles. The key feature of the rapid updating technique developed is the ability to increment and re-arrange the existing search tree reducing the amount of computation taken to find a new plan. The rapid updating techniques developed are combined into a receding horizon control and compared to full cold start method. The rapid updating technique demonstrated an average 62% solve time improvement over a cold start. The rapid updating method is also demonstrated for removal of obstacles from the environment and very large scale problems with 60 obstacles.