Improving gearshift controllers for electric vehicles with reinforcement learning

@article{Beaudoin2022ImprovingGC,
  title={Improving gearshift controllers for electric vehicles with reinforcement learning},
  author={Marc-Antoine Beaudoin and Beno{\^i}t Boulet},
  journal={ArXiv},
  year={2022},
  volume={abs/2112.00529}
}

Figures from this paper

Learning-based synthesis of robust linear time-invariant controllers
TLDR
A robust control framework is used to derive robust stability criteria and simulated policy rollouts are used to obtain gradients on the controller parameters, which serve to improve the closed-loop performance.

References

SHOWING 1-10 OF 43 REFERENCES
Embedded Nonlinear Model Predictive Control of Dual-Clutch Transmissions With Multiple Groups on a Shrinking Horizon
TLDR
Simulations against a high-fidelity model and runtime results demonstrate the performance of the MPC scheme for gear downshift and upshift as well as the algorithmic efficiency with computation times in the single-digit millisecond range on an ECU level.
Optimal control of gear shift operations in automatic transmissions
Design of Clutch-Slip Controller for Automatic Transmission Using Backstepping
To improve the shift quality of vehicles with clutch-to-clutch gearshifts, a nonlinear controller using backstepping technique is designed for the clutch-slip control. Model uncertainties including
Model-based policy search for automatic tuning of multivariate PID controllers
TLDR
PILCO is extended, a model-based policy search framework, to automatically tune multivariate PID controllers purely based on data observed on an otherwise unknown system, rendering PID tuning possible as the solution of a finite horizon optimal control problem without further a priori knowledge.
Analysis and simulation of the gearshift methodology for a novel two-speed transmission system for electric powertrains with a central motor
Electric vehicle powertrains traditionally consist of a central electric motor drive, a single-speed transmission and a differential. This electric powertrain layout, for use in either fully electric
Cooperative Control of Drive Motor and Clutch for Gear Shift of Hybrid Electric Vehicles With Dual-Clutch Transmission
TLDR
A new shift control strategy based on the feedback of both speed and torque states is implemented to improve the shift quality and a robust multivariable control scheme using H-infinity loop shaping is suggested, especially for the inertia phase control.
Learning to Control a Low-Cost Manipulator using Data-Efficient Reinforcement Learning
TLDR
It is demonstrated how a low-cost off-the-shelf robotic system can learn closed-loop policies for a stacking task in only a handful of trials-from scratch.
...
1
2
3
4
5
...