Work

GraphDistNet: A Graph-Based Collision-Distance Estimator for Gradient-Based Trajectory Optimization

Year: 2022

Type: article

Abstract: Trajectory optimization (TO) aims to find a sequence of valid states while minimizing costs. However, its fine validation process is often costly due to computationally expensive collision searches, otherwise coarse searches lower the safety of the system losing a precise solution. To resolve the issues, we introduce a new collision-distance estimator, GraphDistNet, that can precisely encode the structural information between two geometries by leveraging edge feature-based convolutional operations, and also efficiently predict a batch of collision distances and gradients through 25,000 random environments with a maximum of 20 unforeseen objects. Further, we show the adoption of attention mechanism enables our method to be easily generalized in unforeseen complex geometries toward TO. Our evaluation show GraphDistNet outperforms state-of-the-art baseline methods in both simulated and real world tasks.

Source: IEEE Robotics and Automation Letters

DOI: 10.1109/lra.2022.3196956

Authors: Yeseung Kim, Jinwoo Kim, Daehyung Park

Institution: Korea Advanced Institute of Science and Technology

Language: English

Topic: Robotic Path Planning Algorithms

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: National Research Foundation of Korea, Ministry of Science and ICT, South Korea

Awards: G4163670459, G6390257013