High-definition map (HD map) construction is a crucial problem for autonomous driving. This problem typically involves collecting high-quality point clouds, fusing multiple point clouds of the same scene, annotating map elements, and updating maps co
nstantly. This pipeline, however, requires a vast amount of human efforts and resources which limits its scalability. Additionally, traditional HD maps are coupled with centimeter-level accurate localization which is unreliable in many scenarios. In this paper, we argue that online map learning, which dynamically constructs the HD maps based on local sensor observations, is a more scalable way to provide semantic and geometry priors to self-driving vehicles than traditional pre-annotated HD maps. Meanwhile, we introduce an online map learning method, titled HDMapNet. It encodes image features from surrounding cameras and/or point clouds from LiDAR, and predicts vectorized map elements in the birds-eye view. We benchmark HDMapNet on the nuScenes dataset and show that in all settings, it performs better than baseline methods. Of note, our fusion-based HDMapNet outperforms existing methods by more than 50% in all metrics. To accelerate future research, we develop customized metrics to evaluate map learning performance, including both semantic-level and instance-level ones. By introducing this method and metrics, we invite the community to study this novel map learning problem. We will release our code and evaluation kit to facilitate future development.
Thermo-optic microheater is indispensable in silicon photonic devices for smart and reconfigurable photonic networks. Much efforts have been made to improve the metallic microheater performance in the past decades. However, because of the metallic na
ture of light absorption, placing the metallic microheater very close to the waveguide for fast response is impractical and has not been done experimentally. Here, we experimentally demonstrate a metallic microheater placed very close to the waveguide based on parity-time (PT) symmetry breaking. The intrinsic high loss of metallic heater ensures the system will operate in the PT-symmetry-broken region, which guarantee the low loss of light in the silicon waveguide. Moreover, heating at a close range significantly reduces the response time. A fast response time of ~1 us is achieved without introducing extra loss. The insertion loss is only 0.1 dB for the long heater. The modulation bandwidth is 280 kHz, which is an order of magnitude improvement when compared with that of the mainstream thermo-optic phase shifters. To verify the capability of large-scale integration, a 1*8 phased array for beam steering is also demonstrated experimentally with the PT-symmetry-broken metallic heaters. Our work provides a novel design concept for low-loss fast-response optical switches with dissipative materials and offers a new approach to enhance the performance of thermo-optic phase shifters.
