Path Planning for Bulldozers with Curvature Constraints

There is presently no solution to the problem of an autonomous bulldozer pushing mounds of material to desired goal locations in the presence of obstacles whilst obeying the kinematic constraints of the bulldozer. Past work has solved some aspects of this problem, but not all. This research presents the first complete, practical solution to the problem. It works by creating a fixed RRT in advance, and then during operation connecting pushing poses into this RRT using Bezier curves. The RRT algorithm leverages a novel data structure for performing nearest neighbour comparisons for Ackermann-steering vehicles; termed the Distmetree. The resulting pushing states are searched using greedy heuristic search to find a solution and the final path is smoothed with cubic Bezier curves. The mode of operation chosen for best performance also constructs bidirectional RRTs to reach difficult to access pushing poses. The final mode of the algorithm was tested in simulation and proven to be able to solve a wide variety of maps in a few minutes while obeying bulldozer kinematic constraints. The algorithm, whilst not optimal, is complete which is the more desirable property in industry, and the solutions it produces are both feasible and reasonable.

Path Planning for Bulldozers with Curvature Constraints

There is presently no solution to the problem of an autonomous bulldozer pushing mounds of material to desired goal locations in the presence of obstacles whilst obeying the kinematic constraints of the bulldozer. Past work has solved some aspects of this problem, but not all. This research presents the first complete, practical solution to the problem. It works by creating a fixed RRT in advance, and then during operation connecting pushing poses into this RRT using Bezier curves. The RRT algorithm leverages a novel data structure for performing nearest neighbour comparisons for Ackermann-steering vehicles; termed the Distmetree. The resulting pushing states are searched using greedy heuristic search to find a solution and the final path is smoothed with cubic Bezier curves. The mode of operation chosen for best performance also constructs bidirectional RRTs to reach difficult to access pushing poses. The final mode of the algorithm was tested in simulation and proven to be able to solve a wide variety of maps in a few minutes while obeying bulldozer kinematic constraints. The algorithm, whilst not optimal, is complete which is the more desirable property in industry, and the solutions it produces are both feasible and reasonable.

Ecological landscapes guide the assembly of optimal microbial communities

Assembling optimal microbial communities is key for various applications in biofuel production, agriculture, and human health. Finding the optimal community is challenging because the number of possible communities grows exponentially with the number of species, and so an exhaustive search cannot be performed even for a dozen species. A heuristic search that improves community function by adding or removing one species at a time is more practical, but it is unknown whether this strategy can discover an optimal or nearly optimal community. Using consumer-resource models with and without cross-feeding, we investigate how the efficacy of search depends on the distribution of resources, niche overlap, cross-feeding, and other aspects of community ecology. We show that search efficacy is determined by the ruggedness of the appropriately-defined ecological landscape. We identify specific ruggedness measures that are both predictive of search performance and robust to noise and low sampling density. The feasibility of our approach is demonstrated using experimental data from a soil microbial community. Overall, our results establish the conditions necessary for the success of the heuristic search and provide concrete design principles for building high-performing microbial consortia.

Development of Computational Approaches with a Fragment-Based Drug Design Strategy: In Silico Hsp90 Inhibitors Discovery

A semi-exhaustive approach and a heuristic search algorithm use a fragment-based drug design (FBDD) strategy for designing new inhibitors in an in silico process. A deconstruction reconstruction process uses a set of known Hsp90 ligands for generating new ones. The deconstruction process consists of cutting off a known ligand in fragments. The reconstruction process consists of coupling fragments to develop a new set of ligands. For evaluating the approaches, we compare the binding energy of the new ligands with the known ligands.

Dynamic Pathfinding for a Swarm Intelligence Based UAV Control Model Using Particle Swarm Optimisation

In recent years unmanned aerial vehicles (UAVs) have become smaller, cheaper, and more efficient, enabling the use of multiple autonomous drones where previously a single, human-operated drone would have been used. This likely includes crisis response and search and rescue missions. These systems will need a method of navigating unknown and dynamic environments. Typically, this would require an incremental heuristic search algorithm, however, these algorithms become increasingly computationally and memory intensive as the environment size increases. This paper used two different Swarm Intelligence (SI) algorithms: Particle Swarm Optimisation and Reynolds flocking to propose an overall system for controlling and navigating groups of autonomous drones through unknown and dynamic environments. This paper proposes Particle Swarm Optimisation Pathfinding (PSOP): a dynamic, cooperative algorithm; and, Drone Flock Control (DFC): a modular model for controlling systems of agents, in 3D environments, such that collisions are minimised. Using the Unity game engine, a real-time application, simulation environment, and data collection apparatus were developed and the performances of DFC-controlled drones—navigating with either the PSOP algorithm or a D* Lite implementation—were compared. The simulations do not consider UAV dynamics. The drones were tasked with navigating to a given target position in environments of varying size and quantitative data on pathfinding performance, computational and memory performance, and usability were collected. Using this data, the advantages of PSO-based pathfinding were demonstrated. PSOP was shown to be more memory efficient, more successful in the creation of high quality, accurate paths, more usable and as computationally efficient as a typical incremental heuristic search algorithm when used as part of a SI-based drone control model. This study demonstrated the capabilities of SI approaches as a means of controlling multi-agent UAV systems in a simple simulation environment. Future research may look to apply the DFC model, with the PSOP algorithm, to more advanced simulations which considered environment factors like atmospheric pressure and turbulence, or to real-world UAVs in a controlled environment.

RnkHEU: A Hybrid Feature Selection Method for Predicting Students’ Performance

Predicting students’ performance is one of the most concerned issues in education data mining (EDM), which has received more and more attentions. Feature selection is the key step to build prediction model of students’ performance, which can improve the accuracy of prediction and help to identify factors that have significant impact on students’ performance. In this paper, a hybrid feature selection method named rank and heuristic (RnkHEU) was proposed. This novel feature selection method generates the set of candidate features by scoring and ranking firstly and then uses heuristic method to generate the final results. The experimental results show that the four major evaluation criteria have similar performance in predicting students’ performance, and the heuristic search strategy can significantly improve the accuracy of prediction compared with forward search method. Because the proposed RnkHEU integrates ranking-based forward and heuristic search, it can further improve the accuracy of predicting students’ performance with commonly used classifiers about 10% and improve the precision of predicting students’ academic failure by up to 45%.