Deep, spatially coherent Inverse Sensor Models with Uncertainty Incorporation using the evidential Framework
This addresses the need for faster and more reliable sensor data processing in autonomous vehicles, though it appears incremental as it builds on existing evidential frameworks.
The paper tackles the problem of sparse, noisy radar detections in autonomous cars by using evidential convolutional neural networks to compute dense, spatially coherent environment state inference, resulting in denser environment perception in fewer time steps.
To perform high speed tasks, sensors of autonomous cars have to provide as much information in as few time steps as possible. However, radars, one of the sensor modalities autonomous cars heavily rely on, often only provide sparse, noisy detections. These have to be accumulated over time to reach a high enough confidence about the static parts of the environment. For radars, the state is typically estimated by accumulating inverse detection models (IDMs). We employ the recently proposed evidential convolutional neural networks which, in contrast to IDMs, compute dense, spatially coherent inference of the environment state. Moreover, these networks are able to incorporate sensor noise in a principled way which we further extend to also incorporate model uncertainty. We present experimental results that show This makes it possible to obtain a denser environment perception in fewer time steps.