Modal Uncertainty

Modal uncertainty, the presence of multiple possible outcomes or behaviors in a system, is a significant challenge in various fields, particularly autonomous driving and multi-agent systems. Current research focuses on developing robust methods to handle this uncertainty, employing techniques like Bayesian games, model predictive control (incorporating learning-based multimodal predictors), and curriculum learning within multi-agent reinforcement learning frameworks. These approaches aim to improve decision-making and control in uncertain environments by explicitly modeling and managing the different possible future states, leading to safer and more efficient systems in applications ranging from autonomous vehicles to human-computer interaction.

Papers

September 21, 2024

Integrated Decision Making and Trajectory Planning for Autonomous Driving Under Multimodal Uncertainties: A Bayesian Game Approach
Zhenmin Huang, Tong Li, Shaojie Shen, Jun Ma
Autonomous Driving Decision Making Trajectory Planning Bayesian Game Coarse Correlated Equilibrium Modal Uncertainty

May 6, 2024

Motion Planning under Uncertainty: Integrating Learning-Based Multi-Modal Predictors into Branch Model Predictive Control
Mohamed-Khalil Bouzidi, Bojan Derajic, Daniel Goehring, Joerg Reichardt
Autonomous Vehicle Motion Planning High Uncertainty Anticipation Multi Modal Traffic Environment Modal Uncertainty

October 31, 2023

Predictive Control for Autonomous Driving with Uncertain, Multi-modal Predictions
Siddharth H. Nair, Hotae Lee, Eunhyek Joa, Yan Wang, H. Eric Tseng, Francesco Borrelli
Autonomous Driving Autonomous Vehicle Multi Modal Predictive Control Path Planning Uncertain Reasoning Based Collision Modal Uncertainty Stochastic MPC

October 12, 2023

Robustness to Multi-Modal Environment Uncertainty in MARL using Curriculum Learning
Aakriti Agrawal, Rohith Aralikatti, Yanchao Sun, Furong Huang
Native Robustness Multi Agent Reinforcement Learning Multi Agent System Curriculum Learning Multi Agent Reinforcement Modal Uncertainty

September 28, 2023

Robust Safe Control with Multi-Modal Uncertainty
Tianhao Wei, Liqian Ma, Ravi Pandya, Changliu Liu
Modal Uncertainty Robust Safe

July 30, 2023

Uncertainty-Encoded Multi-Modal Fusion for Robust Object Detection in Autonomous Driving
Yang Lou, Qun Song, Qian Xu, Rui Tan, Jianping Wang
Autonomous Driving Object Detection Multi Modal Fusion LiDAR Camera Fusion Robust Object Detection Modal Uncertainty

October 11, 2022

MAP: Multimodal Uncertainty-Aware Vision-Language Pre-training Model
Yatai Ji, Junjie Wang, Yuan Gong, Lin Zhang, Yanru Zhu, Hongfa Wang, Jiaxing Zhang, Tetsuya Sakai, Yujiu Yang
Full Model Vision Language mAP Visual Entailment Multimodal Semantic Modal Uncertainty

June 12, 2022

COLD Fusion: Calibrated and Ordinal Latent Distribution Fusion for Uncertainty-Aware Multimodal Emotion Recognition
Mani Kumar Tellamekala, Shahin Amiriparian, Björn W. Schuller, Elisabeth André, Timo Giesbrecht, Michel Valstar
Emotion Recognition Audio Visual Emotion Prediction Constrained Decoding Global Calibration Modal Uncertainty Ordinal Latent

Modal Uncertainty

Papers

Integrated Decision Making and Trajectory Planning for Autonomous Driving Under Multimodal Uncertainties: A Bayesian Game Approach

Motion Planning under Uncertainty: Integrating Learning-Based Multi-Modal Predictors into Branch Model Predictive Control

Predictive Control for Autonomous Driving with Uncertain, Multi-modal Predictions

Robustness to Multi-Modal Environment Uncertainty in MARL using Curriculum Learning

Robust Safe Control with Multi-Modal Uncertainty

Uncertainty-Encoded Multi-Modal Fusion for Robust Object Detection in Autonomous Driving

MAP: Multimodal Uncertainty-Aware Vision-Language Pre-training Model

COLD Fusion: Calibrated and Ordinal Latent Distribution Fusion for Uncertainty-Aware Multimodal Emotion Recognition