NMNoushin Mehdipour

Noushin Mehdipour

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Noushin Mehdipour has a total of 34 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Quantifying the Satisfaction of Spatio-Temporal Logic Specifications for Multiagent Control

    by Wenliang Liu, Suhail Alsalehi, Noushin Mehdipour, Ezio Bartocci, Calin Belta

    In this article, we study control synthesis problems for multiagent systems (MASs) that must comply with spatio-temporal logic requirements. We define a logic called team spatio-temporal reach and escape logic (t-STREL) and a robustness metric for it that is continuous everywhere and differentiable almost everywhere. These properties facilitate the use of gradient-based optimization and learning-based control techniques, offering greater efficiency compared to traditional gradient-free methods. We propose three approaches leveraging these robustness properties to control the MAS. The first combines a gradient-based optimization algorithm with a heuristic one (hybrid optimization). The second uses imitation learning to learn a recurrent neural network (RNN) controller from a dataset generated by off-line optimizations. The third approach employs a model-based policy search algorithm to learn an RNN controller directly without a dataset. We showcase our proposed approaches in a simulated example. We demonstrate that, with hybrid optimization, the MAS can achieve a high success rate of compliance with the t-STREL requirement, while the imitation learning approach can be used for real-time control. The model-based policy search approach can concurrently achieve both objectives within a relatively short training time.


  • Generalized Mean Robustness for Signal Temporal Logic

    by Noushin Mehdipour, Cristian-Ioan Vasile, Calin Belta

    Robustness functions provide quantitative scores to measure the satisfaction of temporal logic formulas. We introduce a general class of parameterized robustness functions for Signal Temporal Logic (STL), and demonstrate how it can be used for control problems involving STL specifications. We employ power means and generalized functional means to capture robust satisfaction over space and time. We show that our general definition encompasses many of the STL robustness functions in the literature. Most importantly, we show how that our notion of robustness addresses the two main limitations of the the traditional robustness (masking and locality), which currently limit using robustness-based approaches for control. The proposed robustness function parameters affect the conservativeness of the score, and can be chosen based on desired performance. We show how the proposed robustness can be used for control.


  • Recurrent Neural Network Controllers for Signal Temporal Logic Specifications Subject to Safety Constraints

    by Wenliang Liu, Noushin Mehdipour, Calin Belta

    We propose a framework based on Recurrent Neural Networks (RNNs) to determine an optimal control strategy for a discrete-time system that is required to satisfy specifications given as Signal Temporal Logic (STL) formulae. RNNs can store information of a system over time, thus, enable us to determine satisfaction of the dynamic temporal requirements specified in STL formulae. Given a STL formula, a dataset of satisfying system executions and corresponding control policies, we can use RNNs to predict a control policy at each time based on the current and previous states of system. We use Control Barrier Functions (CBFs) to guarantee the safety of the predicted control policy. We validate our theoretical formulation and demonstrate its performance in an optimal control problem subject to partially unknown safety constraints through simulations.


  • Top Cited Papers
    Open Access

    Machine learning enables design automation of microfluidic flow-focusing droplet generation

    by Ali Lashkaripour, Christopher Rodriguez, Noushin Mehdipour, Rizki Mardian, David McIntyre, Luis Ortiz, Joshua Campbell, Douglas Densmore

    Droplet-based microfluidic devices hold immense potential in becoming inexpensive alternatives to existing screening platforms across life science applications, such as enzyme discovery and early cancer detection. However, the lack of a predictive understanding of droplet generation makes engineering a droplet-based platform an iterative and resource-intensive process. We present a web-based tool, DAFD, that predicts the performance and enables design automation of flow-focusing droplet generators. We capitalize on machine learning algorithms to predict the droplet diameter and rate with a mean absolute error of less than 10 μm and 20 Hz. This tool delivers a user-specified performance within 4.2% and 11.5% of the desired diameter and rate. We demonstrate that DAFD can be extended by the community to support additional fluid combinations, without requiring extensive machine learning knowledge or large-scale data-sets. This tool will reduce the need for microfluidic expertise and design iterations and facilitate adoption of microfluidics in life sciences.


  • Specifying User Preferences Using Weighted Signal Temporal Logic

    by Noushin Mehdipour, Cristian-Ioan Vasile, Calin Belta

    We extend Signal Temporal Logic (STL) to enable the specification of importance and priorities. The extension, called Weighted STL (wSTL), has the same qualitative (Boolean) semantics as STL, but additionally defines weights associated with Boolean and temporal operators that modulate its quantitative semantics (robustness). We show that the robustness of wSTL can be defined as weighted generalizations of all known compatible robustness functionals (i.e., robustness scores that are recursively defined over formulae) that can take into account the weights in wSTL formulae. We utilize this weighted robustness to distinguish signals with respect to a desired wSTL formula that has subformulae with different importance or priorities and time preferences, and demonstrate its usefulness in problems with conflicting tasks where satisfaction of all tasks cannot be achieved. We also employ wSTL robustness in an optimization framework to synthesize controllers that maximize satisfaction of a specification with user specified preferences.


  • Control from Signal Temporal Logic Specifications with Smooth Cumulative Quantitative Semantics

    by Iman Haghighi, Noushin Mehdipour, Ezio Bartocci, Calin Belta

    We present a framework to synthesize control policies for nonlinear dynamical systems from complex temporal constraints specified in a rich temporal logic called Signal Temporal Logic (STL). We propose a novel smooth STL quantitative semantics called cumulative robustness, and efficiently compute control policies through a series of smooth optimization problems that are solved using gradient ascent algorithms. Furthermore, we demonstrate how these techniques can be incorporated in a model predictive control framework. The advantages of combining the cumulative robustness function with smooth optimization methods as well as model predictive control are illustrated in case studies.


  • Average-based Robustness for Continuous-Time Signal Temporal Logic

    by Noushin Mehdipour, Cristian-Ioan Vasile, Calin Belta

    We propose a new robustness score for continuous-time Signal Temporal Logic (STL) specifications. Instead of considering only the most severe point along the evolution of the signal, we use average scores to extract more information from the signal, emphasizing robust satisfaction of all the specifications’ subformulae over their entire time interval domains. We demonstrate the advantages of this new score in falsification and control synthesis problems in systems with complex dynamics and multi-agent systems.


  • Open Access

    Genetic design automation for autonomous formation of multicellular shapes from a single cell progenitor

    by Evan Appleton, Noushin Mehdipour, Tristan Daifuku, Demarcus Briers, Iman Haghighi, Michael Moret, George Chao, Timothy Wannier, Anush Chiappino-Pepe, Jeremy Huang, et al.

    A bstract: Multi-cellular organisms originate from a single cell, ultimately giving rise to mature organisms of heterogeneous cell type composition in complex structures. Recent work in the areas of stem cell biology and tissue engineering have laid major groundwork in the ability to convert certain types of cells into other types, but there has been limited progress in the ability to control the morphology of cellular masses as they grow. Contemporary approaches to this problem have included the use of artificial scaffolds, 3D bioprinting, and complex media formulations, however, there are no existing approaches to controlling this process purely through genetics and from a single-cell starting point. Here we describe a computer-aided design approach for designing recombinase-based genetic circuits for controlling the formation of multi-cellular masses into arbitrary shapes in human cells.


  • Open Access

    Average-based Robustness for Continuous-Time Signal Temporal Logic

    by Noushin Mehdipour, Cristian-Ioan Vasile, Calin Belta

    We propose a new robustness score for continuous-time Signal Temporal Logic (STL) specifications. Instead of considering only the most severe point along the evolution of the signal, we use average scores to extract more information from the signal, emphasizing robust satisfaction of all the specifications' subformulae over their entire time interval domains. We demonstrate the advantages of this new score in falsification and control synthesis problems in systems with complex dynamics and multi-agent systems.