Perception Latency

Perception latency, the delay between sensing and acting, is a critical challenge across various fields, from autonomous vehicles to speech processing. Current research focuses on mitigating this latency through novel algorithms and architectures, including deep learning models that predict future actions based on current observations and hybrid neural network approaches combining the strengths of ANNs and SNNs for low-power, low-latency applications. Addressing perception latency is crucial for improving the responsiveness and efficiency of real-time systems, impacting areas such as robotics, AI, and human-computer interaction. Optimizing the trade-off between latency and accuracy is a key focus, leading to the development of sophisticated scheduling and resource allocation strategies.

Papers

November 4, 2024

Enhancing Indoor Mobility with Connected Sensor Nodes: A Real-Time, Delay-Aware Cooperative Perception Approach
Minghao Ning, Yaodong Cui, Yufeng Yang, Shucheng Huang, Zhenan Liu, Ahmad Reza Alghooneh, Ehsan Hashemi, Amir Khajepour
Cooperative Perception LiDAR Camera Fusion Sensor Node Smart Mobility Perception Latency

July 23, 2024

PLM-Net: Perception Latency Mitigation Network for Vision-Based Lateral Control of Autonomous Vehicles
Aws Khalil, Jaerock Kwon
Autonomous Vehicle Vision Based Low Latency PLM Based Lateral Control Perception Latency

March 18, 2024

Reinforcement Learning from Delayed Observations via World Models
Armin Karamzade, Kyungmin Kim, Montek Kalsi, Roy Fox
Reinforcement Learning World Model Partial Observability C POMDPs Standard Reinforcement Learning Perception Latency

January 24, 2024

January 8, 2024

DDD: A Perceptually Superior Low-Response-Time DNN-based Declipper
Jayeon Yi, Junghyun Koo, Kyogu Lee
Structured Output Speech Quality Perception Latency

May 22, 2023

Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline
Zangwei Zheng, Xiaozhe Ren, Fuzhao Xue, Yang Luo, Xin Jiang, Yang You
Large Language Model LLM Inference Inference Acceleration Perception Latency

March 24, 2023

A Hybrid ANN-SNN Architecture for Low-Power and Low-Latency Visual Perception
Asude Aydin, Mathias Gehrig, Daniel Gehrig, Davide Scaramuzza
Spiking Neural Network Low Power Classical Neural Network Bio Inspired Neural Network Perception Latency

November 7, 2022

Peak-First CTC: Reducing the Peak Latency of CTC Models by Applying Peak-First Regularization
Zhengkun Tian, Hongyu Xiang, Min Li, Feifei Lin, Ke Ding, Guanglu Wan
Low Latency CTC Based Theoretical Peak Performance Analysis Prototype Based Regularization Perception Latency