State of the Field
Recent advancements in autonomous vehicle technology are increasingly focused on enhancing safety and efficiency through innovative control and perception strategies. For instance, new reinforcement learning approaches are optimizing path tracking by dynamically adjusting parameters in real-time, improving performance across diverse driving conditions without the need for extensive retuning. Concurrently, the integration of satellite imagery with camera data is revolutionizing high-definition map construction, significantly boosting accuracy in challenging environments. Additionally, novel frameworks are synthesizing tactile data from visual inputs, enhancing vehicles' ability to respond to road conditions proactively. Collaborative safety mechanisms are being developed to facilitate safer lane changes in congested traffic, while multi-objective reinforcement learning is refining decision-making for heavy-duty trucks by balancing safety and efficiency. These developments collectively address critical challenges in autonomous driving, paving the way for more reliable and adaptable systems that can operate effectively in complex real-world scenarios.
Papers
1–9 of 9Learning to Tune Pure Pursuit in Autonomous Racing: Joint Lookahead and Steering-Gain Control with PPO
Pure Pursuit (PP) is widely used in autonomous racing for real-time path tracking due to its efficiency and geometric clarity, yet performance is highly sensitive to how key parameters-lookahead dista...
SatMap: Revisiting Satellite Maps as Prior for Online HD Map Construction
Online high-definition (HD) map construction is an essential part of a safe and robust end-to-end autonomous driving (AD) pipeline. Onboard camera-based approaches suffer from limited depth perception...
Synesthesia of Vehicles: Tactile Data Synthesis from Visual Inputs
Autonomous vehicles (AVs) rely on multi-modal fusion for safety, but current visual and optical sensors fail to detect road-induced excitations which are critical for vehicles' dynamic control. Inspir...
A Collaborative Safety Shield for Safe and Efficient CAV Lane Changes in Congested On-Ramp Merging
Lane changing in dense traffic is a significant challenge for Connected and Autonomous Vehicles (CAVs). Existing lane change controllers primarily either ensure safety or collaboratively improve traff...
Robustness Is a Function, Not a Number: A Factorized Comprehensive Study of OOD Robustness in Vision-Based Driving
Out of distribution (OOD) robustness in autonomous driving is often reduced to a single number, hiding what breaks a policy. We decompose environments along five axes: scene (rural/urban), season, wea...
DiffusionHarmonizer: Bridging Neural Reconstruction and Photorealistic Simulation with Online Diffusion Enhancer
Simulation is essential to the development and evaluation of autonomous robots such as self-driving vehicles. Neural reconstruction is emerging as a promising solution as it enables simulating a wide ...
RENEW: Risk- and Energy-Aware Navigation in Dynamic Waterways
We present RENEW, a global path planner for Autonomous Surface Vehicle (ASV) in dynamic environments with external disturbances (e.g., water currents). RENEW introduces a unified risk- and energy-awar...
Multi-Objective Reinforcement Learning for Efficient Tactical Decision Making for Trucks in Highway Traffic
Balancing safety, efficiency, and operational costs in highway driving poses a challenging decision-making problem for heavy-duty vehicles. A central difficulty is that conventional scalar reward form...
Li-ViP3D++: Query-Gated Deformable Camera-LiDAR Fusion for End-to-End Perception and Trajectory Prediction
End-to-end perception and trajectory prediction from raw sensor data is one of the key capabilities for autonomous driving. Modular pipelines restrict information flow and can amplify upstream errors....