Title:
自律走行車両ためのニューラル・タスク計画部
Document Type and Number:
Japanese Patent JP7169328
Kind Code:
B2
Abstract:
Described herein are embodiments of a neural network-based task planner (TaskNet) for autonomous vehicle. Given a high-level task, the TaskNet planner decomposes it into a sequence of sub-tasks, each of which is further decomposed into task primitives with specifications. TaskNet comprises a first model for predicating the global sequence of working area to cover large terrain, and a second model for determining local operation order and specifications for each operation. The neural models may include convolutional layers for extracting features from grid map-based environment representation, and fully connected layers to combine extracted features with past sequences and predict the next sub-task or task primitive. Embodiments of the TaskNet are trained using an excavation trace generator and evaluate its performance using a 3D physically-based terrain and excavator simulator. Experiment results show TaskNet may effectively learn common task decomposition strategies and generate suitable sequences of sub-tasks and task primitives.
Inventors:
Liang Jun Chang
Jin Shin Jao
Jin Shin Jao
Application Number:
JP2020174568A
Publication Date:
November 10, 2022
Filing Date:
October 16, 2020
Export Citation:
Assignee:
Baidu USA LLC
International Classes:
E02F3/43; E02F9/20; G05D1/02; G06T7/00
Domestic Patent References:
| JP2018147261A | ||||
| JP4293404A |
Foreign References:
| US20190129436 | ||||
| US6076030 |
Attorney, Agent or Firm:
Patent Attorney Corporation Tsukuni
Previous Patent: Imido-based proteolytic modulators and related methods of use
Next Patent: management system
Next Patent: management system