Vehicle Velocity Prediction Using Artificial Neural Network and Effect of Real World Signals on Prediction Window

Gaikwad, Tushar; Rabinowitz, Aaron; Motallebiaraghi, Farhang; Bradley, Thomas H.; Asher, Zachary D.; Fong, A.C.M.; Meyer, Rick

doi:10.4271/2020-01-0729

Cited by 18 publications

(11 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the last several decades, within the exploitation of Artificial Intelligence (AI), ML applied to ADAS systems has started to be more and more common. Successful applications have been reported for vehicle velocity prediction [31,32], lane detection [33], ACC [34], ECO-ACC [35], lane changing detection [36] and EMS with V2x connectivity [37]. This widespread diffusion is mainly due to the algorithms' ability to properly predict and identify a wide range of behaviours.…”

Section: Predictionmentioning

confidence: 99%

A Review of Model Predictive Controls Applied to Advanced Driver-Assistance Systems

et al. 2021

View full text Add to dashboard Cite

Advanced Driver-Assistance Systems (ADASs) are currently gaining particular attention in the automotive field, as enablers for vehicle energy consumption, safety, and comfort enhancement. Compelling evidence is in fact provided by the variety of related studies that are to be found in the literature. Moreover, considering the actual technology readiness, larger opportunities might stem from the combination of ADASs and vehicle connectivity. Nevertheless, the definition of a suitable control system is not often trivial, especially when dealing with multiple-objective problems and dynamics complexity. In this scenario, even though diverse strategies are possible (e.g., Equivalent Consumption Minimization Strategy, Rule-based strategy, etc.), the Model Predictive Control (MPC) turned out to be among the most effective ones in fulfilling the aforementioned tasks. Hence, the proposed study is meant to produce a comprehensive review of MPCs applied to scenarios where ADASs are exploited and aims at providing the guidelines to select the appropriate strategy. More precisely, particular attention is paid to the prediction phase, the objective function formulation and the constraints. Subsequently, the interest is shifted to the combination of ADASs and vehicle connectivity to assess for how such information is handled by the MPC. The main results from the literature are presented and discussed, along with the integration of MPC in the optimal management of higher level connection and automation. Current gaps and challenges are addressed to, so as to possibly provide hints on future developments.

show abstract

Section: Predictionmentioning

confidence: 99%

A Review of Model Predictive Controls Applied to Advanced Driver-Assistance Systems

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Based on this collected evidence, it was concluded that an LSTM should be used within the POEMS system. For further discussions and details, the reader is referred to the team's previous publications [26,27]. [42], a-ECMS [11], as well as their derivatives, and (2) those based on DP.…”

Section: Subsystem 1: Perceptionmentioning

confidence: 99%

“…Despite all of this research, a thorough investigation of the datasets and prediction models' effect on vehicle FE (the full system) has not been conducted. The latest research has explored the effect on velocity prediction error metrics rather than resultant vehicle FE [26,27]. In order to facilitate real-world implementation, certain specific research gaps must be addressed; these research gaps are defined in [16] as:…”

Section: Introductionmentioning

confidence: 99%

“…[26,32] showed that high-fidelity predictions were possible through the use of deep Long Short-Term-Memory (LSTM) ANNs. Finally, in 2020, a thorough analysis of various combinations of real-world data streams and machine learning techniques [26,27,33] showed that the highest degree of prediction fidelity could be attained through the use of LSTM ANNs with the use of signal phase and timing (SPaT) and lead vehicle data.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Development and Evaluation of Velocity Predictive Optimal Energy Management Strategies in Intelligent and Connected Hybrid Electric Vehicles

et al. 2021

Self Cite

View full text Add to dashboard Cite

In this study, a thorough and definitive evaluation of Predictive Optimal Energy Management Strategy (POEMS) applications in connected vehicles using 10 to 20 s predicted velocity is conducted for a Hybrid Electric Vehicle (HEV). The presented methodology includes synchronous datasets gathered in Fort Collins, Colorado using a test vehicle equipped with sensors to measure ego vehicle position and motion and that of surrounding objects as well as receive Infrastructure to Vehicle (I2V) information. These datasets are utilized to compare the effect of different signal categories on prediction fidelity for different prediction horizons within a POEMS framework. Multiple artificial intelligence (AI) and machine learning (ML) algorithms use the collected data to output future vehicle velocity prediction models. The effects of different combinations of signals and different models on prediction fidelity in various prediction windows are explored. All of these combinations are ultimately addressed where the rubber meets the road: fuel economy (FE) enabled from POEMS. FE optimization is performed using Model Predictive Control (MPC) with a Dynamic Programming (DP) optimizer. FE improvements from MPC control at various prediction time horizons are compared to that of full-cycle DP. All FE results are determined using high-fidelity simulations of an Autonomie 2010 Toyota Prius model. The full-cycle DP POEMS provides the theoretical upper limit on fuel economy (FE) improvement achievable with POEMS but is not currently practical for real-world implementation. Perfect prediction MPC (PP-MPC) represents the upper limit of FE improvement practically achievable with POEMS. Real-Prediction MPC (RP-MPC) can provide nearly equivalent FE improvement when used with high-fidelity predictions. Constant-Velocity MPC (CV-MPC) uses a constant speed prediction and serves as a “null” POEMS. Results showed that RP-MPC, enabled by high-fidelity ego future speed prediction, led to significant FE improvement over baseline nearly matching that of PP-MPC.

show abstract

“…Currently, a variety of algorithms have been spurred to achieve speed prediction, including Kalman filter [10], exponential method [11], autoregressive moving average (ARMA) methods [12], particle filter [13], stochastic forecast [14], and machine learning algorithms [15]. Amongst them, Markov chain (MC) based prediction algorithms and neural networks (NNs), belonging to stochastic forest and machine learning filed, are most attractive and widely exploited [16]. Actually, future driving condition of vehicle can be estimated based on inner correlation between the current step and previous one or multi moments.…”

Section: Introductionmentioning

confidence: 99%

Prediction of vehicle driving conditions with incorporation of stochastic forecasting and machine learning and a case study in energy management of plug-in hybrid electric vehicles

Liu

Gao

et al. 2021

Mechanical Systems and Signal Processing

View full text Add to dashboard Cite

Prediction of short-term future driving conditions can contribute to energy management of plug-in hybrid electric vehicles and subsequent improvement of their fuel economy. In this study, a fused short-term forecasting model for driving conditions is established by incorporating the stochastic forecasting and machine learning. The Markov chain is applied to calculate the transition probability of historical driving data, by which the stochastic prediction is conducted based on the Monte Carlo algorithm. Then, a neural network is employed to learn the current driving information and main knowledge after the simplified correlation of characteristic parameters, and meanwhile the genetic algorithm is adopted to optimize the initial weight and thresholds of networks. Finally, the short-term velocity prediction is achieved by combining them, and the overall performance is evaluated by four typical criteria. Simulation results indicate that the proposed fusion algorithm outperforms the single Markov model, the radial basis function neural network and the back propagation neural network with respect to the prediction precision and the difference distribution between expectation and prediction values. In addition, a case study is conducted by applying the built prediction algorithm in energy management of a plug-in hybrid electric vehicle, and simulation results highlight that the proposed algorithm can supply preferable velocity prediction, thereby facilitating improvement of the operating economy of the vehicle.

show abstract

Vehicle Velocity Prediction Using Artificial Neural Network and Effect of Real World Signals on Prediction Window

Cited by 18 publications

References 22 publications

A Review of Model Predictive Controls Applied to Advanced Driver-Assistance Systems

A Review of Model Predictive Controls Applied to Advanced Driver-Assistance Systems

Development and Evaluation of Velocity Predictive Optimal Energy Management Strategies in Intelligent and Connected Hybrid Electric Vehicles

Prediction of vehicle driving conditions with incorporation of stochastic forecasting and machine learning and a case study in energy management of plug-in hybrid electric vehicles

Contact Info

Product

Resources

About