TransParking: A Dual-Decoder Transformer Framework with Soft Localization for End-to-End Automatic Parking
This work addresses the critical need for precise vehicle parking in intelligent transportation, offering an incremental improvement over existing methods.
The paper tackles the problem of automatic parking in complex environments by proposing a purely vision-based transformer model that directly outputs future trajectory coordinates from camera data, achieving approximately 50% reduction in errors compared to the state-of-the-art end-to-end trajectory prediction algorithm.
In recent years, fully differentiable end-to-end autonomous driving systems have become a research hotspot in the field of intelligent transportation. Among various research directions, automatic parking is particularly critical as it aims to enable precise vehicle parking in complex environments. In this paper, we present a purely vision-based transformer model for end-to-end automatic parking, trained using expert trajectories. Given camera-captured data as input, the proposed model directly outputs future trajectory coordinates. Experimental results demonstrate that the various errors of our model have decreased by approximately 50% in comparison with the current state-of-the-art end-to-end trajectory prediction algorithm of the same type. Our approach thus provides an effective solution for fully differentiable automatic parking.