Search papers, labs, and topics across Lattice.
This paper introduces a novel method for enabling anytime computing in deep neural networks (DNNs) for LiDAR object detection, allowing dynamic scaling of input resolution based on operational timing requirements. By utilizing a single memory-efficient DNN model and a deadline-aware scheduler, the approach predicts execution times for various resolutions, optimizing performance without the overhead of multiple models. Experimental results on the nuScenes dataset show that this method significantly outperforms existing techniques, facilitating collision-free navigation in simulated autonomous driving scenarios.
A single DNN model can dynamically adjust input resolution for LiDAR object detection, achieving superior performance and efficiency in real-time applications.
Making tradeoffs between execution latency and result utility (i.e., anytime computing) for adapting to dynamic operational requirements has been shown to enhance the performance of cyber-physical systems. In this work, we focus on enabling anytime computing for deep neural networks (DNNs) that process LiDAR point clouds for 3D object detection. We propose a novel method that enables multi-resolution inference for models that process point clouds as pillars or voxels, allowing the input to be dynamically scaled and processed at the resolution needed to meet timing requirements. Importantly, our memory-efficient approach requires the deployment of only a single DNN model, avoiding the need to deploy multiple models, each trained for a different input resolution. We also introduce a deadline-aware scheduler that selects the highest possible resolution for any given input by accurately predicting the execution time for all possible resolutions at runtime, which is challenging due to the irregularity of LiDAR point clouds. Experimental results on the nuScenes autonomous driving dataset demonstrate that our method significantly outperforms existing anytime computing approaches for LiDAR object detection. Finally, we deploy our approach in a simulated autonomous driving system, where it consistently enables collision-free navigation while avoiding unnecessary stalls caused by environmental complexity.
