Learning Adaptive Driving Behavior Using Recurrent Deterministic Policy Gradients

Mani, Kaustubh; Kaushik, Meha; Singhania, Nirvan; Krishna, K. Madhava

doi:10.1109/robio49542.2019.8961480

Cited by 3 publications

(2 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the implementation of the RDPG model for different applications, which require a more rapid and accurate response compared to the forecasting, verifies the suitability of the RDPG. Consequently, the RDPG was applied to control traffic lights in transportation [73], learn adaptive behavior in driving [74], perform adaptive trading for different markets [75], and to reduce errors of robot positions and joint torques [42]. These applications of the RDPG algorithm signify that the RDPG based ISVR model is feasible for both offline and real-time applications in any type of complex environment.…”

Section: Results and Comparative Analysismentioning

confidence: 99%

A Multistage Hybrid Model ICEEMDAN-SE-VMD-RDPG for a Multivariate Solar Irradiance Forecasting

Sibtain

Saleem

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Accuracy of solar irradiance forecasting is imperative for the effective utilization and integration of solar energy into the power system. To forecast global horizontal irradiance based on a multivariate meteorological data; this study first evaluates five standalone models, including recurrent deterministic policy gradient (RDPG), long short term memory (LSTM) neural network, extreme gradient boosting (XGB), Gaussian process regression (GPR), and support vector regression (SVR). The RDPG model outperforms the standalone counterparts by demonstrating 2.485 W/m 2 , 20.591 W/m 2 , 18.316 W/m 2 , and 23.176 W/m 2 reductions in RMSE compared to the LSTM, XGB, GPR, and SVR models. Afterward, the performance of the RDPG model is further enhanced, by developing two-stage hybrid models, including improved complete ensemble empirical mode decomposition with additive noise-RDPG (ICEEMDAN-RDPG) and variational mode decomposition-RDPG (VMD-RDPG). The subsequent construction of the hybrid model ICEEMDAN-SE-VMD-RDPG (ISVR) results in the further improvement of the two-stage hybrid models. The ISVR surpasses all the established models including VMD-RDPG, ICEEMDAN-RDPG, RDPG, LSTM, XGB, GPR, and SVR by displaying 18.401 W/m 2 , 13.908 W/m 2 , 33.223 W/m 2 , 53.111 W/m 2 , 67.704 W/m 2 , 67.502 W/m 2 and 69.943 W/m 2 , respectively, decrease in RMSE. The overall results are enlightening and reveal the extension feasibility of the IVSR model for the other forecasting tasks, e.g., renewable energy integration and electrical load forecasting. INDEX TERMS Solar irradiance forecasting, decomposition techniques, sample entropy, correlation, deep reinforcement learning.

show abstract

Section: Results and Comparative Analysismentioning

confidence: 99%

A Multistage Hybrid Model ICEEMDAN-SE-VMD-RDPG for a Multivariate Solar Irradiance Forecasting

Sibtain

Saleem

et al. 2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…By formulating the problem as a Partially Observable Markov Decision Process (POMDP) and utilizing a Recurrent Neural Network (RNN) to consider temporal information, the agent in the RL algorithm is allowed to learn from the patterns of variance in the environment, e.g., from sensor noise, other perception limitations, or surrounding vehicle behavior, and handle the uncertainty accordingly [43,44]. To develop adaptive driving behavior, Mani et al [45] used recurrent deterministic policy gradients to train the agent how to react to the surrounding traffic condition instead of the normal DDPG. For controlling longitudinal vehicle motion specifically, Zhou et al [46] proposed a car-following model which can react to the preceding dynamics by predicting traffic oscillation using RNNs.…”

Section: B Acc Measurement Uncertaintymentioning

confidence: 99%

Adaptive Cruise Control Utilizing Noisy Multi-Leader Measurements: A Learning-Based Approach

Ni,

Knoop,

Kooij

et al. 2024

IEEE Open J. Intell. Transp. Syst.

View full text Add to dashboard Cite

A substantial number of vehicles nowadays are equipped with adaptive cruise control (ACC), which adjusts the vehicle speed automatically. However, experiments have found that commercial ACC systems which only detect the direct leader amplify the propagating disturbances in the platoon. This can cause severe traffic congestion when the number of ACC-equipped vehicles increases. Therefore, an ACC system which also considers the second leader further downstream is required. Such a system enables the vehicle to achieve multi-anticipation and hence ensure better platoon stability. Nevertheless, measurements collected from the second leader may be comparatively inaccurate given the limitations of current state-ofthe-art sensor technology. This study adopts deep reinforcement learning to develop ACC controllers that besides the input from the first leader exploits the additional information obtained from the second leader, albeit noisy. The simulation experiment demonstrates that even under the influence of noisy measurements, the multi-leader ACC platoon shows smaller disturbance and jerk amplitudes than the one-leader ACC platoon, indicating improved string stability and ride comfort. Practical takeaways are twofold: first, the proposed method can be used to further develop multi-leader ACC systems. Second, even noisy data from the second leader can help stabilize traffic, which makes such systems viable in practice.

show abstract

On-Ramp Merging for Connected Autonomous Vehicles using Deep Reinforcement Learning

Mahabal

Fang

Wang

2022

2022 IEEE International Conferences on Internet of Things (iThings) and IEEE Green Computing &Amp; Communications (GreenCom) An

View full text Add to dashboard Cite

Learning Adaptive Driving Behavior Using Recurrent Deterministic Policy Gradients

Cited by 3 publications

References 3 publications

A Multistage Hybrid Model ICEEMDAN-SE-VMD-RDPG for a Multivariate Solar Irradiance Forecasting

A Multistage Hybrid Model ICEEMDAN-SE-VMD-RDPG for a Multivariate Solar Irradiance Forecasting

Adaptive Cruise Control Utilizing Noisy Multi-Leader Measurements: A Learning-Based Approach

On-Ramp Merging for Connected Autonomous Vehicles using Deep Reinforcement Learning

Contact Info

Product

Resources

About