A lightweight, pure-Python mobile robot simulator designed for experiments in Artificial Intelligence (AI) and Machine Learning, especially for Jupyter Notebooks

Overview

aitk.robots

PyPI version CI build status

A lightweight Python robot simulator for JupyterLab, Notebooks, and other Python environments.

Goals

  1. A lightweight mobile robotics simulator
  2. Usable in the classroom, research, or exploration
  3. Explore wheeled robots with range, cameras, smell, and light sensors
  4. Operate quickly without a huge amount of resources
  5. Create reproducible experiments
  6. Designed for exposition, experimentation, and analysis
  7. Sensors designed for somewhat realistic problems (such as image recognition)
  8. Especially designed to work easily with Machine Learning and Artificial Intelligence systems

Installation

For the core operations, you will need to install just aitk.robots:

pip install aitk.robots

To use the Jupyter enhancements, you'll also need the browser-based extensions. You can install those with:

jupyter labextension install @jupyter-widgets/jupyterlab-manager

If not in a conda environment, then you will also need to:

jupyter nbextension enable --py widgetsnbextension

For additional information, please see:

Comments
  • View of camera's width in watched world does not change when width is changed

    View of camera's width in watched world does not change when width is changed

    I'm not sure if this is an important issue, but when you change a robot's camera width from 256 to 64, for example, the view of the robot in a watched world (the lines that trace the camera's view) don't change.

    opened by lmeeden1 2
  • Update robot.py

    Update robot.py

    Minor wording changes for clarity to robot movement commands "amount" -> "speed". Also added clarity to robot constructor parameter color.

    opened by lmeeden1 1
  • watching a recorder generates a new error

    watching a recorder generates a new error

    recorder.watch()

    generates an error


    TypeError Traceback (most recent call last) ~/opt/miniconda3/envs/py38/lib/python3.8/site-packages/aitk/robots/watchers.py in (widget) 540 layout=Layout(width="100%"), 541 ) --> 542 controls.on_displayed(lambda widget: self.initialize()) 543 return controls 544

    ~/opt/miniconda3/envs/py38/lib/python3.8/site-packages/aitk/robots/watchers.py in initialize(self) 547 Setup the displayer ids to map results to the areas. 548 """ --> 549 results = self.function(self.control_slider.value) 550 if not isinstance(results, (list, tuple)): 551 results = [results]

    ~/opt/miniconda3/envs/py38/lib/python3.8/site-packages/aitk/robots/watchers.py in goto(self, time) 380 self.world._reset_ground_image() 381 self.world.update() --> 382 picture = self.world.display(format="image") 383 return picture 384

    TypeError: display() got an unexpected keyword argument 'format' ​

    opened by lmeeden1 1
  • problem with watching and saving a recorder

    problem with watching and saving a recorder

    The following code generates the error message below. The save_as method also has the same issue.

    recorder = world.record()
    world.seconds(120,[wander_ir, wander_laser, search_light],real_time=False)
    recorder.watch()
    

    AttributeError Traceback (most recent call last) ~/opt/miniconda3/envs/py38/lib/python3.8/site-packages/aitk/robots/watchers.py in (widget) 540 layout=Layout(width="100%"), 541 ) --> 542 controls.on_displayed(lambda widget: self.initialize()) 543 return controls 544

    ~/opt/miniconda3/envs/py38/lib/python3.8/site-packages/aitk/robots/watchers.py in initialize(self) 547 Setup the displayer ids to map results to the areas. 548 """ --> 549 results = self.function(self.control_slider.value) 550 if not isinstance(results, (list, tuple)): 551 results = [results]

    ~/opt/miniconda3/envs/py38/lib/python3.8/site-packages/aitk/robots/watchers.py in goto(self, time) 378 if self.world.time == 0: 379 # In case it changed: --> 380 self.world.reset_ground_image() 381 self.world.update() 382 picture = self.world.display(format="image")

    AttributeError: 'World' object has no attribute 'reset_ground_image'

    opened by lmeeden1 1
  • Checklist for 1.0 release

    Checklist for 1.0 release

    • [x] robot's camera can see a bulb through a wall
    • [x] smell sensors and light sensors both show up as small circles on the robot; makes it hard to distinguish between the two. Perhaps the smell sensors could be squares?
    • [x] As a robot equipped with a camera approaches food, when it is quite close to the food it becomes invisible (not showing up in the image).
    • [x] device constructors should raise exception when given an unknown parameter
    • [x] single-line wall issues: don't block smell, don't save with config
    • [x] watched views should have a blue border
    • [x] need to test GroundCamera, pen_up() and pen_down()
    • [x] draw light in world (top-down view) so that it hits walls rather than drawing under them
    • [x] bring docs up to date
    • [ ] Colab issues
      • [x] no-joystick button grid is overlapping
      • [ ] joystick control in colab
    • [x] Recorder issues
      • [x] recording should use max_trace_length
      • [x] might be an issue with recorder.get_trace() to get a long trace
      • [x] smells/food and bulb on/off aren't integrated with recorder
      • [x] recorder doesn't play last step
    • [ ] why does "Resetting seed" show an increasing number of times?
    opened by dsblank 0
Releases(v0.9.21)
  • v0.9.21(May 26, 2021)

    Major changes:

    • Fixed bug in not showing full last recorder step
    • Don't call attr on backend (error from colab)
    • Fixes traces in recorder
    • Added recorder.watch(width)
    • Fixed issues with recorder and food
    • Added bulb.flip(), bulb.on()/off()
    • Added world.get_food()
    Source code(tar.gz)
    Source code(zip)
  • v0.9.17(May 19, 2021)

    Major changes:

    • Added bulb on/off and eat food to events
    • Updated docs
    • Added color_sensitivity to LightSensor
    • Reset target and velocities to zero when set_pose
    • Fix get smell typo
    Source code(tar.gz)
    Source code(zip)
  • 0.9.9(Apr 29, 2021)

  • v0.9.6(Apr 18, 2021)

    Major changes:

    • Camera food and bulb fixes (bug when min/max wrapped around unit circle)
    • Camera food and bulbs no alpha
    • Camera food is rectangle; bulb is circle
    • Add a ground image automatically with robot.pen_down() if there is None
    • Renamed Robot.info() and World.info() to .summary()
    • Light sensors are yellow; food sensors are white
    • Raise exception for invalid device config
    • Draw single wall lines with thickness
    • Get walls from config correctly
    • Fixed single wall config save
    • Fixed WHITE changing
    Source code(tar.gz)
    Source code(zip)
  • v0.9.5(Apr 8, 2021)

    Major changes:

    • Only recompute spread of food smell when food or walls change
    • Automatically compute smell_cell_size based on world size
    • Added robot.eat() - returns True if successful; must be close enough to food (20 pixels, robot.eat_food_distance), increases robot.food_eaten
    Source code(tar.gz)
    Source code(zip)
  • v0.9.4(Apr 7, 2021)

  • v0.9.3(Apr 7, 2021)

    Majors changes:

    * default for blub brightness is now 50
    * change bulb state will update the world
    * food is visible in camera and in world view (food is white)
    * added new World(smell_cell_size) size of smell grid, in pixels (larger is more coarse)
    * improved World.info()
    
    Source code(tar.gz)
    Source code(zip)
  • v0.9.2(Apr 6, 2021)

  • v0.9.1(Apr 1, 2021)

  • v0.8.12(Apr 1, 2021)

  • v0.8.11(Mar 31, 2021)

  • v0.8.10(Mar 25, 2021)

    Major changes:

    • Added Bulb device for robots
    • Added bulb.on() and bulb.off() for all bulbs
    • See bulbs in camera view (under development to make look better)
    • Robot's LightSensor device can sense bulbs on robots
    Source code(tar.gz)
    Source code(zip)
  • v0.8.9(Mar 25, 2021)

    Major changes:

    • Bulbs now have names
    • Added world.bulbs, world.get_bulb(name or index)
    • Added robot.add_device_ring()
    • Removed bqplot from setup
    • Added world.add_wall(color, x1, y1, x2, y2, box=False)
    • Added Vehicle robot type
    Source code(tar.gz)
    Source code(zip)
  • v0.8.8(Mar 24, 2021)

    Major changes:

    • Add light with transparency to camera image (in progress)
    • Fixed bug in seeing obstacles in camera
    • Made robots height bigger in camera image
    Source code(tar.gz)
    Source code(zip)
  • v0.8.7(Mar 18, 2021)

    Major changes:

    • Draft of seeing light in camera view
    • Give warning if not enough robot control functions
    • LightSensors show as white
    • removed robot.turn()
    • 0 to 1 only values: robot.forward(), robot.backward()
    • Renamed world.step to _step
    • Changed robot.move() to require two values
    • Added robot.motors(l, r)
    • Renamed camera.a to camera.fov
    • Removed the display from recorder.save_as()
    • Renamed LightSensor.get_reading() to get_brightness()

    This version will need an updated aitk.utils so Joystick will match Robot.move

    Source code(tar.gz)
    Source code(zip)
  • v0.8.6(Mar 17, 2021)

  • v0.8.5(Mar 17, 2021)

  • v0.8.4(Mar 15, 2021)

  • v0.8.3(Mar 14, 2021)

  • v0.8.2(Mar 13, 2021)

  • v0.8.1(Mar 13, 2021)

    Major changes:

    • made many attributes "private" (renamed with leading underscore)
    • removed camera viewport; set defaults
    • don't allow extra keywords for world and robot
    • updated worlds with direction -> a
    Source code(tar.gz)
    Source code(zip)
  • v0.8.0(Mar 12, 2021)

    Major changes:

    • Added Robot.get_velocity(target=False)
    • Don't color entire robot when stalled; now just border is white
    • Robot.reverse() flips all velocities (vx, va)
    • Added Robot.rotate() and Robot.translate(); same as Robot.turn() and Robot.forward()
    • Renamed all take_picture() to get_image(), returning a PIL Image
    • Renamed all direct to a (in robot and devices)
    • You can draw on world with world.canvas.draw_line(), draw_circle(), etc.
    • Camera images are less curved than before
    Source code(tar.gz)
    Source code(zip)
  • v0.7.7(Mar 9, 2021)

  • v0.7.6(Mar 9, 2021)

    Major changes:

    • Fixed Robot direction coords in constructor and JSON in/out
    • Added Camera.orthographic (distance is to camera plane) vs. perspective mode (distance is to camera point)
    Source code(tar.gz)
    Source code(zip)
  • v0.7.5(Mar 6, 2021)

    Major changes:

    • requires aitk.utils
    • Adjust Playback buttons
    • Always inject CSS; clean up watchers
    • CameraWatcher takes layout kwargs; move(t, r, quiet)
    • Added world.run(background=True)
    • world.stop()
    • world.status
    • display(format)
    • get_widget()
    Source code(tar.gz)
    Source code(zip)
  • v0.7.4(Mar 5, 2021)

  • v0.7.3(Mar 5, 2021)

    Major changes:

    • Allow robot.move(T, R) to ignore None values (to control one or the other)
    • Changed World.add_bulb() to take args, not Bulb object
    Source code(tar.gz)
    Source code(zip)
  • v0.7.2(Mar 4, 2021)

    Major changes:

    • Changed camera angle from 60 to 30
    • Changed colorsFadeWithDistance 0.5 to 0.9
    • Changed cameraShape from [256, 128] to [64, 32]
    • Changed robot.get_pose(), set_pose() and repr to be counter-clockwise positive
    • Renamed world.take_picture() to world.display()
    Source code(tar.gz)
    Source code(zip)
  • v0.7.1(Mar 3, 2021)

  • v0.7.0(Mar 2, 2021)

Machine Learning algorithms implementation.

Machine Learning Algorithms Machine Learning algorithms implementation. What can I find here? ML Algorithms KNN K-Means-Clustering SVM (MultiClass) Pe

David Levin 1 Dec 10, 2021
A fast, pure python implementation of the MuyGPs Gaussian process realization and training algorithm.

Fast implementation of the MuyGPs Gaussian process hyperparameter estimation algorithm MuyGPs is a GP estimation method that affords fast hyperparamet

Lawrence Livermore National Laboratory 13 Dec 02, 2022
FLIght SCheduling OPTimization - a simple optimization library for flight scheduling and related problems in the discrete domain

Fliscopt FLIght SCheduling OPTimization 🛫 or fliscopt is a simple optimization library for flight scheduling and related problems in the discrete dom

33 Dec 17, 2022
A lightweight, pure-Python mobile robot simulator designed for experiments in Artificial Intelligence (AI) and Machine Learning, especially for Jupyter Notebooks

aitk.robots A lightweight Python robot simulator for JupyterLab, Notebooks, and other Python environments. Goals A lightweight mobile robotics simulat

3 Oct 22, 2021
PICO is an algorithm for exploiting Reinforcement Learning (RL) on Multi-agent Path Finding tasks.

PICO is an algorithm for exploiting Reinforcement Learning (RL) on Multi-agent Path Finding tasks. It is developed by the Multi-Agent Artificial Intel

21 Dec 20, 2022
All Algorithms implemented in Python

The Algorithms - Python All algorithms implemented in Python (for education) These implementations are for learning purposes only. Therefore they may

The Algorithms 150.6k Jan 03, 2023
Policy Gradient Algorithms (One Step Actor Critic & PPO) from scratch using Numpy

Policy Gradient Algorithms From Scratch (NumPy) This repository showcases two policy gradient algorithms (One Step Actor Critic and Proximal Policy Op

1 Jan 17, 2022
Algorithms written in different programming languages

Data Structures and Algorithms Clean example implementations of data structures and algorithms written in different languages. List of implementations

Zoran Pandovski 1.3k Jan 03, 2023
Our implementation of Gillespie's Stochastic Simulation Algorithm (SSA)

SSA Our implementation of Gillespie's Stochastic Simulation Algorithm (SSA) Requirements python =3.7 numpy pandas matplotlib pyyaml Command line usag

Anoop Lab 1 Jan 27, 2022
An implementation of ordered dithering algorithm in python as multimedia course project

One way of minimizing the size of an image is to simply reduce the number of bits you use to represent each pixel.

7 Dec 02, 2022
Solving a card game with three search algorithms: BFS, IDS, and A*

Search Algorithms Overview In this project, we want to solve a card game with three search algorithms. In this card game, we have to sort our cards by

Korosh 5 Aug 04, 2022
A simple python implementation of A* and bfs algorithm solving Eight-Puzzle

A simple python implementation of A* and bfs algorithm solving Eight-Puzzle

2 May 22, 2022
HashDB is a community-sourced library of hashing algorithms used in malware.

HashDB HashDB is a community-sourced library of hashing algorithms used in malware. How To Use HashDB HashDB can be used as a stand alone hashing libr

OALabs 216 Jan 06, 2023
All algorithms implemented in Python for education

The Algorithms - Python All algorithms implemented in Python - for education Implementations are for learning purposes only. As they may be less effic

1 Oct 20, 2021
A library for benchmarking, developing and deploying deep learning anomaly detection algorithms

A library for benchmarking, developing and deploying deep learning anomaly detection algorithms Key Features • Getting Started • Docs • License Introd

OpenVINO Toolkit 1.5k Jan 04, 2023
A Python description of the Kinematic Bicycle Model with an animated example.

Kinematic Bicycle Model Abstract A python library for the Kinematic Bicycle model. The Kinematic Bicycle is a compromise between the non-linear and li

Winston H. 36 Dec 23, 2022
Python package to monitor the power consumption of any algorithm

CarbonAI This project aims at creating a python package that allows you to monitor the power consumption of any python function. Documentation The com

Capgemini Invent France 36 Nov 11, 2022
This is the code repository for 40 Algorithms Every Programmer Should Know , published by Packt.

40 Algorithms Every Programmer Should Know, published by Packt

Packt 721 Jan 02, 2023
Python algorithm to determine the optimal elevation threshold of a GNSS receiver, by using a statistical test known as the Brown-Forsynthe test.

Levene and Brown-Forsynthe: Test for variances Application to Global Navigation Satellite Systems (GNSS) Python algorithm to determine the optimal ele

Nicolas Gachancipa 2 Aug 09, 2022
This python algorithm creates a simple house floor plan based on a user-provided CSV file.

This python algorithm creates a simple house floor plan based on a user-provided CSV file. The algorithm generates possible router placements and evaluates where a signal will be reached in every roo

Joshua Miller 1 Nov 12, 2021