PlanAgent: A Multi-modal Large Language Agent for Closed-loop Vehicle Motion Planning
Vehicle motion planning is an essential component of autonomous driving technology.
Current rule-based vehicle motion planning methods perform satisfactorily in common …
Current rule-based vehicle motion planning methods perform satisfactorily in common …
SemanticFormer: Holistic and Semantic Traffic Scene Representation for Trajectory Prediction using Knowledge Graphs
Trajectory prediction in autonomous driving relies on accurate representation of all relevant
contexts of the driving scene including traffic participants, road topology, traffic signs as well …
contexts of the driving scene including traffic participants, road topology, traffic signs as well …
Tractable Joint Prediction and Planning over Discrete Behavior Modes for Urban Driving
Significant progress has been made in training multimodal trajectory forecasting models for
autonomous driving. However, effectively integrating these models with downstream …
autonomous driving. However, effectively integrating these models with downstream …
Multiagent trajectory prediction with global‐local scene‐enhanced social interaction graph network
Trajectory prediction is essential for intelligent autonomous systems like autonomous
driving, behavior analysis, and service robotics. Deep learning has emerged as the …
driving, behavior analysis, and service robotics. Deep learning has emerged as the …
JointMotion: Joint Self-supervision for Joint Motion Prediction
We present JointMotion, a self-supervised learning method for joint motion prediction in
autonomous driving. Our method includes a scene-level objective connecting motion and …
autonomous driving. Our method includes a scene-level objective connecting motion and …
[PDF][PDF] Offline Learning for Stochastic Multi-Agent Planning in Autonomous Driving
A Villaflor - 2024 - kilthub.cmu.edu
Fully autonomous vehicles have the potential to greatly reduce vehicular accidents and
revolutionize how people travel and how we transport goods. Many of the major challenges …
revolutionize how people travel and how we transport goods. Many of the major challenges …
[PDF][PDF] A Study on Designing a Deep Reinforcement Learning Library towards Practical Applications
T Seno - 2023 - koara.lib.keio.ac.jp
Deep reinforcement learning (RL) has shown significant advancements in various domains.
Building a reusable library is essential to accelerate the research and development process …
Building a reusable library is essential to accelerate the research and development process …
[PDF][PDF] Gameformer planner: A learning-enabled interactive prediction and planning framework for autonomous vehicles
Decision-making is a fundamental yet challenging task for autonomous vehicles, as it
requires accurate predictions of other traffic participants and, above all, safe and interactive …
requires accurate predictions of other traffic participants and, above all, safe and interactive …
[PDF][PDF] DACAPO: Accelerating Continuous Learning in Autonomous Systems for Video Analytics
YKCOJ Hwang, WKS Oh, YLH Sharma… - jongse-park.github.io
Deep neural network (DNN) video analytics is crucial for autonomous systems such as self-
driving vehicles, unmanned aerial vehicles (UAVs), and security robots. However, real-world …
driving vehicles, unmanned aerial vehicles (UAVs), and security robots. However, real-world …
Dynamic Voxels Based on Ego-Conditioned Prediction: An Integrated Spatio-Temporal Framework for Motion Planning
T Zhang, M Fu, W Song, Y Yang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Prediction is a vital component of motion planning for autonomous vehicles (AVs). By
reasoning about the possible behavior of other target agents, the ego vehicle (EV) can …
reasoning about the possible behavior of other target agents, the ego vehicle (EV) can …