English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In end-to-end autonomous driving, the utilization of existing sensor fusiontechniques and navigational control methods for imitation learning provesinadequate in challenging situations that involve numerous dynamic agents. Toaddress this issue, we introduce LeTFuser, a lightweight transformer-basedalgorithm for fusing multiple RGB-D camera representations. To performperception and control tasks simultaneously, we utilize multi-task learning.Our model comprises of two modules, the first being the perception module thatis responsible for encoding the observation data obtained from the RGB-Dcameras. Our approach employs the Convolutional vision Transformer (CvT)\cite{wu2021cvt} to better extract and fuse features from multiple RGB camerasdue to local and global feature extraction capability of convolution andtransformer modules, respectively. Encoded features combined with static anddynamic environments are later employed by our control module to predictwaypoints and vehicular controls (e.g. steering, throttle, and brake). We usetwo methods to generate the vehicular controls levels. The first method uses aPID algorithm to follow the waypoints on the fly, whereas the second onedirectly predicts the control policy using the measurement features andenvironmental state. We evaluate the model and conduct a comparative analysiswith recent models on the CARLA simulator using various scenarios, ranging fromnormal to adversarial conditions, to simulate real-world scenarios. Our methoddemonstrated better or comparable results with respect to our baselines in termof driving abilities. The code is available at\url{https://github.com/pagand/e2etransfuser/tree/cvpr-w} to facilitate futurestudies.

LeTFuser: Light-weight End-to-end Transformer-Based Sensor Fusion for Autonomous Driving with Multi-Task Learning