Linear Quadratic Regulator (LQR) approach for lifting and stabilizing of two-wheeled wheelchair

Ahmad, Salmiah; Tokhi, M. O.

doi:10.1109/icom.2011.5937119

Cited by 23 publications

(20 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [4], the author proposes to estimate the thermal load and use a regulator and a disturbance rejection component to keep the room at comfort temperature. In [12], the author proposes a novel multi-input multi-output (MIMO) to model HVAC system and uses a linear-quadratic regulator (LQR) [3] to optimize control performance and to stabilize the proposed HVAC system. In general, exact modeling of HVAC system dynamics is difficult and several data-driven approaches are proposed recently.…”

Section: Related Workmentioning

confidence: 99%

Building HVAC Scheduling Using Reinforcement Learning via Neural Network Based Model Approximation

Zhang

Kuppannagari

Kannan

et al. 2019

Proceedings of the 6th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation

View full text Add to dashboard Cite

Buildings sector is one of the major consumers of energy in the United States. The buildings HVAC (Heating, Ventilation, and Air Conditioning) systems, whose functionality is to maintain thermal comfort and indoor air quality (IAQ), account for almost half of the energy consumed by the buildings. Thus, intelligent scheduling of the building HVAC system has the potential for tremendous energy and cost savings while ensuring that the control objectives (thermal comfort, air quality) are satisfied.Traditionally, rule-based and model-based approaches such as linear-quadratic regulator (LQR) have been used for scheduling HVAC. However, the system complexity of HVAC and the dynamism in the building environment limit the accuracy, efficiency and robustness of such methods. Recently, several works have focused on model-free deep reinforcement learning based techniques such as Deep Q-Network (DQN). Such methods require extensive interactions with the environment. Thus, they are impractical to implement in real systems due to low sample efficiency. Safetyaware exploration is another challenge in real systems since certain actions at particular states may result in catastrophic outcomes.To address these issues and challenges, we propose a modelbased reinforcement learning approach that learns the system dynamics using a neural network. Then, we adopt Model Predictive Control (MPC) using the learned system dynamics to perform control with random-sampling shooting method. To ensure safe exploration, we limit the actions within safe range and the maximum absolute change of actions according to prior knowledge. We evaluate our ideas through simulation using widely adopted EnergyPlus tool on a case study consisting of a two zone data-center. Experiments show that the average deviation of the trajectories sampled from the learned dynamics and the ground truth is below 20%. Compared with baseline approaches, we reduce the total energy consumption by 17.1% ∼ 21.8%. Compared with model-free reinforcement learning approach, we reduce the required number of training steps to converge by 10x.The energy consumption by buildings consist of 40% of the total energy and 70% of total electricity in the United States [18]. Of the total energy consumption of buildings, the Heating, Ventilation and Air-Conditioning (HVAC) system accounts for 50% while the rest is used for lighting, electrical appliances, electric vehicles, etc. The main objective of the HVAC system is to maintain the indoor temperature and air quality. An intelligent HVAC scheduling system will, additionally, save energy and cost while satisfying the objective. The HVAC system is a nonlinear system and has complex system dynamics with a large number of subsystems including chillers, boilers, heat pumps, pipes, ducts, fans, pumps and heat exchangers [11]. In this paper, we assume the combination of equipment to operate by the HVAC system is fixed and focus on how to set the temperature point for local controllers to reduce the energy arXiv:1910.05313v1 [eess.SY]

show abstract

Section: Related Workmentioning

confidence: 99%

Building HVAC Scheduling Using Reinforcement Learning via Neural Network Based Model Approximation

Zhang

Kuppannagari

Kannan

et al. 2019

Proceedings of the 6th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation

View full text Add to dashboard Cite

show abstract

“…Generally speaking, the member function should be unimodal function. And the distribution overlap rate in discourse domain should be in the range of 0.2~0.6 [10][11][12] . The output member function of Lspeed and Rspeed is shown in Fig.10 and Fig.11.…”

Section: A Fuzzy Set Definitionsmentioning

confidence: 99%

“…More recently, a kind of fuzzy logic control algorithm to lifting up the wheelchair and maintaining stability on platform while on two wheels is being studied [8][9][10]. The mentioned wheelchair is successful solved the problem of adapting to the narrow environment by a fuzzy control system without long adjusting time.…”

Section: Introductionmentioning

confidence: 98%

A fuzzy-model-based gravity center adjustment and inclination control for stair-climbing wheelchair

Wang

Gao

Duan

et al. 2012

Proceedings of the 10th World Congress on Intelligent Control and Automation

View full text Add to dashboard Cite

Balance control is a critical step to ensure tip-over stability for stair-climbing wheelchair. This paper presents a novel fuzzy method for adjusting the gravity center and controlling inclination of a stair-climbing wheelchair. The proposed fuzzy controller is designed based the kinematic relationship between the position of the gravity centre and the obliquity of the wheelchair in obstacle environments. It optimally compensates for changing of the gravity centre by adjusting obliquity of the wheelchair using a pair of actuators. To validate the proposed method, we have carried out simulations and experiments. The results demonstrate that the proposed method can efficiently compensate for changing of the gravity center to prevent the overturn.

show abstract

“…i f P , i Q , are chosen to be symmetry positive semidefinite, and i R to be symmetry positive definite. The QOR optimal control problem is to drive the state vector Finally, based on (39) and (30), PSPID controller is directly tuned for subsystems (23). The formulation makes the proposed controller has both of PID controller and QOR advantages.…”

Section: Optimal Pspidmentioning

confidence: 99%

“…Thus linear controller such as LQR and PID controllers are more favourable for this fast system [19][20][21]. Many researches preferred and showed that the LQR as a modern controller gave better performance compared to conventional PID controller [22][23][24]. However the research overlooked the applicability of LQR controller in input trajectory tracking where the significant state trajectory errors occur [25].…”

Section: Introductionmentioning

confidence: 99%

Dynamic Modelling and Optimal Controlscheme of Wheel Inverted Pendulum for Mobile Robot Application

Shamsudin¹,

Mamat²,

Nawawi³

2013

IJCTCM

View full text Add to dashboard Cite

show abstract

Linear Quadratic Regulator (LQR) approach for lifting and stabilizing of two-wheeled wheelchair

Cited by 23 publications

References 10 publications

Building HVAC Scheduling Using Reinforcement Learning via Neural Network Based Model Approximation

Building HVAC Scheduling Using Reinforcement Learning via Neural Network Based Model Approximation

A fuzzy-model-based gravity center adjustment and inclination control for stair-climbing wheelchair

Dynamic Modelling and Optimal Controlscheme of Wheel Inverted Pendulum for Mobile Robot Application

Contact Info

Product

Resources

About