KNODE-MPC: A Knowledge-Based Data-Driven Predictive Control Framework for Aerial Robots

K. Y. Chee, T. Z. Jiahao and M. A. Hsieh

Abstract: In this letter, we consider the problem of deriving and incorporating accurate dynamic models for model predictive control (MPC) with an application to quadrotor control. MPC relies on precise dynamic models to achieve the desired closed-loop performance. However, the presence of uncertainties in complex systems and the environments they operate in poses a challenge in obtaining sufficiently accurate representations of the system dynamics. In this letter, we make use of a deep learning tool, knowledge-based neural ordinary differential equations (KNODE), to augment a model obtained from first principles. The resulting hybrid model encompasses both a nominal first-principle model and a neural network learnt from simulated or real-world experimental data. Using a quadrotor, we benchmark our hybrid model against a state-of-the-art Gaussian Process (GP) model and show that the hybrid model provides more accurate predictions of the quadrotor dynamics and is able to generalize beyond the training data. To improve closed-loop performance, the hybrid model is integrated into a novel MPC framework, known as KNODE-MPC. Results show that the integrated framework achieves 60.2% improvement in simulations and more than 21% in physical experiments, in terms of trajectory tracking performance.

Status: Published in IEEE RA-L. https://doi.org/10.1109/LRA.2022.3144787

Preprint available on arXiv: https://arxiv.org/abs/2109.04821

Learning and Leveraging Features in Flow-Like Environments to Improve Situational Awareness

T. Salam, V. Edwards, and M. A. Hsieh

Abstract: This letter studies how global dynamics and knowledge of high-level features can inform decision-making for robots in flow-like environments. Specifically, we investigate how coherent sets, an environmental feature found in these environments, inform robot awareness within these scenarios. The proposed approach is an online environmental feature generator which can be used for robot reasoning. We compute coherent sets online with techniques from machine learning and design frameworks for robot behavior that leverage coherent set features. We demonstrate the effectiveness of online methods over offline methods. Notably, we apply these online methods for robot monitoring of pedestrian behaviors and robot navigation through water. Environmental features such as coherent sets provide rich context to robots for smarter, more efficient behavior.

Status: Published in IEEE RA-L. https://doi.org/10.1109/LRA.2022.3141762

Preprint available on arXiv: https://arxiv.org/abs/2109.06107

Controlling stochastic switching

Using control to shape stochastic escape and switching dynamics

Dhanushka Kularatne, Eric Forgoston, and M. Ani Hsieh

Abstract: We present a strategy to control the mean stochastic switching times of general dynamical systems with multiple equilibrium states subject to Gaussian white noise. The control can either enhance or abate the probability of escape from the deterministic region of attraction of a stable equilibrium in the presence of external noise. We synthesize a feedback control strategy that actively changes the system’s mean stochastic switching behavior based on the system’s distance to the boundary of the attracting region. With the proposed controller, we are able to achieve a desired mean switching time, even when the strength of noise in the system is not known. The control method is analytically validated using a one-dimensional system, and its effectiveness is numerically demonstrated for a set of dynamical systems of practical importance.

Status: Published online. doi: 10.1063/1.5090113

Coordinating AGVs for Automated Warehouses

Coordination of multiple AGVs: a quadratic optimization method

Valerio Digani, M. Ani Hsieh, Lorenzo Sabattini, and Cristian Secchi

Abstract: This paper presents an optimization strategy to coordinate a fleet of Automated Guided Vehicles (AGVs) traveling on ad-hoc pre-defined roadmaps. Specifically, the objective is to maximize traffic throughput of AGVs navigating in an automated warehouse by minimizing the time AGVs spend negotiating complex traffic patterns to avoid collisions with other AGVs. In this work, the coordination problem is posed as a Quadratic Program where the optimization is performed in a centralized manner. The proposed method is validated by means of simulations and experiments for different industrial warehouse scenarios. The performance of the proposed strategy is then compared with a recently proposed decentralized coordination strategy that relies on local negotiations for shared resources. The results show that the proposed coordination strategy successfully maximizes vehicle throughput and significantly minimizes the time vehicles spend negotiating traffic under different scenarios.

Status: Published in Autonomous Robots.  Preprint to come.

Planning Optimal Paths in General Flows

Going With The Flow: A Graph Based Approach to Optimal Path Planning in General Flows

Dhanushka Kularatne, Subhrajit Bhattacharya, and M. Ani Hsieh

Abstract: Autonomous surface and underwater vehicles (ASVs and AUVs) used for ocean monitoring are typically deployed for long periods of time and must operate with limited energy budgets. Coupled with the increased accessibility to ocean flow data, there has been a significant interest in developing energy efficient motion plans for these vehicles that leverage the dynamics of the surrounding flow. In this paper, we present a graph search based method to plan time and energy optimal paths in static and time-varying flow fields. We also use tools from topological path planning to generate optimal paths in different homotopy classes to facilitate simultaneous exploration of the environment by multi-robot teams. The proposed strategy is validated using analytical flow models, actual ocean data, and in experiments using an indoor laboratory testbed capable of creating flows with ocean-like features. We also present an alternative approach using a Riemannian metric based approximation for the cost functions in the static flow case for computing time and energy optimal paths. The Riemannian approximation results in smoother trajectories in contrast to the graph based strategy while requiring less computational time.

Status: Accepted and to appear in Autonomous Robots. Preprint to come.