Lukas Taus

Lukas Taus, Vrushabh Zinage, Takashi Tanaka et al.

We revisit the problem of motion planning in the Gaussian belief space. Motivated by the fact that most existing sampling-based planners suffer from high computational costs due to the high-dimensional nature of the problem, we propose an approach that leverages a deep learning model to predict optimal path candidates directly from the problem description. Our proposed approach consists of three steps. First, we prepare a training dataset comprising a large number of input-output pairs: the input image encodes the problem to be solved (e.g., start states, goal states, and obstacle locations), whereas the output image encodes the solution (i.e., the ground truth of the shortest path). Any existing planner can be used to generate this training dataset. Next, we leverage the U-Net architecture to learn the dependencies between the input and output data. Finally, a trained U-Net model is applied to a new problem encoded as an input image. From the U-Net's output image, which is interpreted as a distribution of paths,an optimal path candidate is reconstructed. The proposed method significantly reduces computation time compared to the sampling-based baseline algorithm.

Lukas Taus, Richard Tsai, Jeffrey G. Andrews

In a wireless network, the spatial location of the transmitters has a large impact on the achievable rate at each user location. The optimal placement of -- for example -- cellular base stations is a difficult non-convex problem, and is usually addressed with simplified propagation models and simplified heuristics that may account for specifics such as the site topology, building locations, and user density. We propose a mathematically rigorous framework for optimal transmitter placement that explicitly integrates detailed site-specific maps, spatial material properties, and realistic signal attenuation. We introduce a novel aggregated network quality functional which captures the essential trade-off between maximizing network coverage and minimizing cost, and establish the problem's sub-modularity under certain practical conditions. To solve the resulting resource-constrained optimization problem for sparse, discrete transmitter configurations, we propose the Interference-Aware Submodular Placement Algorithm (IA-SPA) and prove theoretical performance guarantees on its gap from optimality. IA-SPA is general and can incorporate existing BS locations and prohibited areas (e.g. a lake), making it useful for either clean-slate or incremental deployments. We show the utility of our approach using a ray tracing-based simulation framework applied to 3D maps of San Francisco and Florence, where we compare to known base station deployments by AT&T, T-Mobile and Iliad. We demonstrate that our proposed placement strategy achieves significant increases in mean data rate (about 2x) and edge rate ($2-8$x) compared to existing tower deployments, using the same number of transmitters.

Lukas Taus, Yen-Hsi Richard Tsai

Sensor placement optimization methods have been studied extensively. They can be applied to a wide range of applications, including surveillance of known environments, optimal locations for 5G towers, and placement of missile defense systems. However, few works explore the robustness and efficiency of the resulting sensor network concerning sensor failure or adversarial attacks. This paper addresses this issue by optimizing for the least number of sensors to achieve multiple coverage of non-simply connected domains by a prescribed number of sensors. We introduce a new objective function for the greedy (next-best-view) algorithm to design efficient and robust sensor networks and derive theoretical bounds on the network's optimality. We further introduce a Deep Learning model to accelerate the algorithm for near real-time computations. The Deep Learning model requires the generation of training examples. Correspondingly, we show that understanding the geometric properties of the training data set provides important insights into the performance and training process of deep learning techniques. Finally, we demonstrate that a simple parallel version of the greedy approach using a simpler objective can be highly competitive.

Lukas Taus, Yen-Hsi Richard Tsai

We address the problem of efficient and unobstructed surveillance or communication in complex environments. On one hand, one wishes to use a minimal number of sensors to cover the environment. On the other hand, it is often important to consider solutions that are robust against sensor failure or adversarial attacks. This paper addresses these challenges of designing minimal sensor sets that achieve multi-coverage constraints -- every point in the environment is covered by a prescribed number of sensors. We propose a greedy algorithm to achieve the objective. Further, we explore deep learning techniques to accelerate the evaluation of the objective function formulated in the greedy algorithm. The training of the neural network reveals that the geometric properties of the data significantly impact the network's performance, particularly at the end stage. By taking into account these properties, we discuss the differences in using greedy and $ε$-greedy algorithms to generate data and their impact on the robustness of the network.