We present a hierarchical control approach for maneuvering an autonomous vehicle (AV) in tightly-constrained environments where other moving AVs and/or human driven vehicles are present. A two-level hierarchy is proposed: a high-level data-driven strategy predictor and a lower-level model-based feedback controller. The strategy predictor maps an encoding of a dynamic environment to a set of high-level strategies via a neural network. Depending on the selected strategy, a set of time-varying hyperplanes in the AV’s position space is generated online and the corresponding halfspace constraints are included in a lower-level model-based receding horizon controller. These strategy-dependent constraints drive the vehicle towards areas where it is likely to remain feasible. Moreover, the predicted strategy also informs switching between a discrete set of policies, which allows for more conservative behavior when prediction confidence is low. We demonstrate the effectiveness of the proposed data-driven hierarchical control framework in a two-car collision avoidance scenario through simulations and experiments on a 1/10 scale autonomous car platform where the strategy-guided approach outperforms a model predictive control baseline in both cases.
more »
« less
Hierarchical MIMO Decoupling Control for Vehicle Roll and Planar Motions With Control Allocation
Although many methods of ground vehicle dynamics control have been widely studied, their robustness against undesirable oscillatory coupling behaviors of planar and roll dynamics is not fully explored. To address this issue, a hierarchical multiple-input-multiple-output (MIMO) decoupling controller is proposed in this study. Based on the hierarchical control configuration, the coupled vehicle roll and planar dynamics are resolved in the high-level control, and a control allocation is utilized for tracking control in the low-level control. The decoupled internal dynamics and nominal stability are then analyzed and proved. Moreover, by using the vehicle yaw rate and load transfer ratio, a control trigger with dynamic weighting is designed to guarantee the feasibility of the MIMO decoupling control and smooth control efforts. Through the co-simulation between CarSim and MATLAB/Simulink, the feasibility and effectiveness of the proposed controller are verified.
more »
« less
- Award ID(s):
- 1828010
- PAR ID:
- 10514441
- Publisher / Repository:
- IEEE
- Date Published:
- Journal Name:
- IEEE Transactions on Vehicular Technology
- Volume:
- 73
- Issue:
- 1
- ISSN:
- 0018-9545
- Page Range / eLocation ID:
- 494 to 503
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Here we present a hybrid hierarchical statistical control approach for the control of robotic manipulators. The bimodal dynamic imaging system considered in this paper utilizes two robotic manipulators to move the source and detector imaging modules. As this system contains both continuous and discrete dynamics, hybrid system control techniques are applied. The robotic arms used in this research are comprised of compliant joints, which have been shown to introduce process noise into the system. To address this, a full-state feedback statistical controller is developed to minimize joint angle variations for the system. The statistical controllers for the two robot arms are then coordinated using a hierarchical controller. Finally, the feasibility of the hybrid hierarchical statistical controller is demonstrated with numerical simulations.more » « less
-
more » « less
Abstract The primary aim of this research paper is to enhance the effectiveness of a two-level infrastructure-based control framework utilized for traffic management in expansive networks. The lower-level controller adjusts vehicle velocities to achieve the desired density determined by the upper-level controller. The upper-level controller employs a novel Lyapunov-based switched Newton extremum seeking control approach to ascertain the optimal vehicle density in congested cells where downstream bottlenecks are unknown, even in the presence of disturbances in the model. Unlike gradient-based approaches, the Newton algorithm eliminates the need for the unknown Hessian matrix, allowing for user-assignable convergence rates. The Lyapunov-based switched approach also ensures asymptotic convergence to the optimal set point. Simulation results demonstrate that the proposed approach, combining Newton’s method with user-assignable convergence rates and a Lyapunov-based switch, outperforms gradient-based extremum seeking in the hierarchical control framework.
-
null (Ed.)Abstract This paper presents a novel architecture for model predictive control (MPC)-based indoor climate control of multi-zone buildings to provide energy efficiency. Unlike prior works, we do not assume the availability of a high-resolution multi-zone building model, which is challenging to obtain. Instead, the architecture uses a low-resolution model of the building that is divided into a small number of “meta-zones” that can be easily identified using existing data-driven modeling techniques. The proposed architecture is hierarchical. At the higher level, an MPC controller uses the low-resolution model to make decisions for the air handling unit (AHU) and the meta-zones. Since the meta-zones are fictitious, a lower level controller converts the high-level MPC decisions into commands for the individual zones by solving a projection problem that strikes a trade-off between two potentially conflicting goals: the AHU-level decisions made by the MPC are respected while the climate of the individual zones is maintained within the comfort bounds. The performance of the proposed controller is assessed via simulations in a high-fidelity simulation testbed and compared to that of a rule-based controller that is used in practice. Simulations in multiple weather conditions show the effectiveness of the proposed controller in terms of energy savings, climate control, and computational tractability.more » « less
-
more » « less
Inspired by the unique neurophysiology of the octopus, a hierarchical framework is proposed that simplifies the coordination of multiple soft arms by decomposing control into high‐level decision‐making, low‐level motor activation, and local reflexive behaviors via sensory feedback. When evaluated in the illustrative problem of a model octopus foraging for food, this hierarchical decomposition results in significant improvements relative to end‐to‐end methods. Performance is achieved through a mixed‐modes approach, whereby qualitatively different tasks are addressed via complementary control schemes. Herein, model‐free reinforcement learning is employed for high‐level decision‐making, while model‐based energy shaping takes care of arm‐level motor execution. To render the pairing computationally tenable, a novel neural network energy shaping (NN‐ES) controller is developed, achieving accurate motions with time‐to‐solutions 200 times faster than previous attempts. The hierarchical framework is then successfully deployed in increasingly challenging foraging scenarios, including an arena littered with obstacles in 3D space, demonstrating the viability of the approach.
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1109/tvt.2023.3308577
