We address the problem of stable and robust control of vehicles with lateral error dynamics for the application of lane keeping. Lane departure is the primary reason for half of the fatalities in road accidents, making the development of stable, adaptive and robust controllers a necessity. Any disturbance or uncertainty introduced to the steering-angle input can be catastrophic for the vehicle. Therefore, controllers must be developed to actively handle such uncertainties. In this work, we introduce a Neural$\mathcal{L}_1$Adaptive controller (Neural-L1) which learns the uncertainties in the lateral error dynamics of a front-steered Ackermann vehicle and guarantees stability and robustness. Our contributions are threefold: i) We extend the theoretical results for guaranteed stability and robustness of conventional$\mathcal{L}_1$Adaptive controllers to Neural-L1; ii) We implement a Neural-L1 for the lane keeping application which learns uncertainties in the dynamics accurately; iii) We evaluate the performance of Neural-L1 on a physics-based simulator, PyBullet, and conduct extensive real-world experiments with the FlTENTH platform to demonstrate superior reference trajectory tracking performance of Neural-L1 compared to other state-of-the-art controllers, in the presence of uncertainties. Our project page, including supplementary material and videos, can be found at https://mukhe027.github.io/Neural-Adaptive-Control/

In this paper, we address the problem of system identification and control of a front-steered vehicle which abides by the Ackermann geometry constraints. This problem arises naturally for on-road and off-road vehicles that require reliable system identification and basic feedback controllers for various applications such as lane keeping and way-point navigation. Traditional system identification requires expensive equipment and is time consuming. In this work we explore the use of differentiable physics for system identification and controller design and make the following contributions: i) We develop a differentiable physics simulator (DPS) to provide a method for the system identification of front-steered class of vehicles whose system parameters are learned using a gradient-based method; ii) We provide results for our gradient-based method that exhibit better sample efficiency in comparison to other gradient-free methods; iii) We validate the learned system parameters by implementing a feedback controller to demonstrate stable lane keeping performance on a real front-steered vehicle, the F1TENTH; iv) Further, we provide results exhibiting comparable lane keeping behavior for system parameters learned using our gradient-based method with lane keeping behavior of the actual system parameters of the F1TENTH.

In this article, we address the problem of coordinating the motion of a team of robots with limited field of view (FOV), which inducesasymmetryin their interactions. In this context, we first propose a general coordinated motion framework for multirobot systems with triangular FOV capable of guaranteeing stability under asymmetric (directed) interactions. In deriving this framework, we illustrate that asymmetry in multirobot interactions can lead to degenerate configurations for which a fully decentralized controller may be insufficient to achieve coordination. Thus, we introduce a switching control mechanism that achievesadaptive decentralization, enabling collaborative behaviors that seek support of a centralized planner for situations that are inherently unstable (degenerate). To demonstrate the generality of our framework we provide a case study involving varying team objectives, such as topology control, that the robots can achieve with limited FOV, while remaining stable. Experimental and numerical validations based on the previously discussed case study are provided to corroborate the theoretical findings

Thousands of scientific publications discuss evidence on the efficacy of non-cancer generic drugs being tested for cancer. However, trying to manually identify and extract such evidence is intractable at scale. We introduce a natural language processing pipeline to automate the identification of relevant studies and facilitate the extraction of therapeutic associations between generic drugs and cancers from PubMed abstracts. We annotate datasets of drug-cancer evidence and use them to train models to identify and characterize such evidence at scale. To make this evidence readily consumable, we incorporate the results of the models in a web application that allows users to browse documents and their extracted evidence. Users can provide feedback on the quality of the evidence extracted by our models. This feedback is used to improve our datasets and the corresponding models in a continuous integration system. We describe the natural language processing pipeline in our application and the steps required to deploy services based on the machine learning models.

In this paper, we address the problem of optimal topology selection for stable coordination of multi-robot systems with asymmetric interactions. This problem arises naturally for multi-robot systems that interact based on sensing, e.g., with limited field of view (FOV) cameras. From our previous efforts on motion control in such settings, we have shown that not all interaction topologies yield stable coordinated motion when asymmetry exists. At the same time, not all robot-to-robot interactions are of equal quality, and thus we seek to optimize asymmetric interaction topologies subject to the constraint that the topology yields stable multi-robot motion. In this context, we formulate an optimal topology selection problem (OTSP) as a mixed integer semidefinite programming (MISDP) problem to compute optimal topologies that yield stable coordinated motion. Simulation results are provided to corroborate the effectiveness of the proposed OTSP formulation.

Recent research has demonstrated the use of the structural connectome as a powerful tool to characterize the network architecture of the brain and potentially generate biomarkers for neurologic and psychiatric disorders. In particular, the anatomic embedding of the edges of the cerebral graph have been postulated to elucidate the relative importance of white matter tracts to the overall network connectivity, explaining the varying effects of localized white matter pathology on cognition and behavior. Here, we demonstrate the use of a linear diffusion model to quantify the impact of these perturbations on brain connectivity. We show that the eigenmodes governing the dynamics of this model are strongly conserved between healthy subjects regardless of cortical and sub-cortical parcellations, but show significant, interpretable deviations in improperly developed brains. More specifically, we investigated the effect of agenesis of the corpus callosum (AgCC), one of the most common brain malformations to identify differences in the effect of virtual corpus callosotomies and the neurodevelopmental disorder itself. These findings, including the strong correspondence between regions of highest importance from graph eigenmodes of network diffusion and nexus regions of white matter from edge density imaging, show converging evidence toward understanding the relationship between white matter anatomy and the structural connectome.