learning-barrier-certificates-for-neural-path-tracking-control-of-self-driving-vehicles-extension

https://github.com/zhizhenqin/learning-barrier-certificates-for-neural-path-tracking-control-of-self-driving-vehicles-extension

Science Score: 26.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (6.2%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

Basic Info
  • Host: GitHub
  • Owner: ZhizhenQin
  • License: mit
  • Default Branch: main
  • Size: 8.57 MB
Statistics
  • Stars: 2
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created almost 5 years ago · Last pushed almost 5 years ago
Metadata Files
Readme License Citation

README.md

Learning Barrier Certificates for Neural Path Tracking Control of Self Driving Vehicles - Extension

An extension of paper Learning Barrier Certificates for Neural Path Tracking Control of Self Driving Vehicles is contained in the PDF file, with the following sections

  1. Pseudocodes
  2. Policy Learning
  3. Learning Low-Dimensional Barriers under Partial Observability
  4. Estimating Range of Dynamics near Samples
  5. Finding Boundary Counterexamples for Retraining
  6. Using the Learned Barrier Function for Safety Monitor
  7. Hyper-parameters and Details of Experiments

Below we present figures contained in the original and extended paper.


Pseudocodes

Training the Barrier Function

Cerifying the Barrier Function

Dynamic Model Trajectories Illustration

Plotting of trajectories of the dynamic model, with x, y axes as angle and distance errors, and z axis as:

Longitudinal Speed | Lateral Speed | Yaw Rate :-------------------------:|:------------------------:|:-------------------------: Dynamic Model Trajectory Longitudinal Speed | Dynamic Model Trajectory Lateral Speed | Dynamic Model Trajectory Yaw Rate


Flow Chart of Overall Pipeline


Vehicle Dynamics Models

Kinematic Model | Dynamic Model
:-------------------------:|:------------------------: Kinematic Model | Dynamic Model


Barrier Functions

The barrier functions on kinematic model, dynamic model and TORCS environment

Kinematic Model (3D) | Dynamic Model (2D) | TORCS (2D) :-------------------------:|:------------------------:|:-------------------------: Kinematic Barrier | Dynamic Barrier | TORCS Barrier


Safety Monitor

Backward reachable states for dynamic model, evaluated on a maximum curvature of 0.15, for 50 time steps

Path with Curvature 0.15 (Curve to Left) | Path with Curvature 0.15 (Curve to Right) | Safety Monitor :-------------------------:|:------------------------:|:-------------------------: Kinematic Barrier | Dynamic Barrier |


Importance of Retraining

The barrier function for dynamic model obtained after the initial training and after the final retraining, projected in the dimensions of angle and distance error

Initial Barrier | Final Barrier
:-------------------------:|:------------------------: Retraining Initial Barrier | Retraining Final Barrier


Vector Fields of Dynamic Model

Close to Collected Trajectories | Whole Certification Grid
:-------------------------:|:------------------------: Vector Field Close | Vector Field Whole Grid


Barrier Behavior of TORCS Environment

Owner

  • Name: Zhizhen Qin
  • Login: ZhizhenQin
  • Kind: user

GitHub Events

Total
Last Year