fsherratt / erl_smartcities_2019 Goto Github PK

T265 arm offset for GoTo
Mission blocks (takeoff, land, fly here)
Victory dance/song
Telemetry GUI, add goto, current, risk map
Telemetry over UDP
LED arduino
Multi-core processing
Visulisations - 3d plot (unity?)
Auto-start script
Dave's d435 mapping suggestions
Multi d435 setup
Interface classes for SITL replacements
Unit-testing
Data-logging
Data review tools
Auto recovery code
Simplify startup code, use python enter
Multi-aircraft?
Config files
Clearer tuning variables
Fix mavlink-thread queue system
Fix 433 telemtry bottleneck during visual tracking
Grid north offset
Generic t265 rotational transform for any Y angle
So many navigation imorovements
The technologys for attractive/repulsive forces

Use built-in python library

https://docs.python.org/2/library/logging.html

Communication with MK Smart Hub for commanding aircraft and ground station

Look into how to do multicore and shared memory stuff in python

The framework supporting all configurations and coordinate i/o.

Abstraction layer and process loop for communication with the PixHawk. Provides a public interface for retrieving and sending telemetry

Generate a 3D map of the environment

consider changing voxel size, adding blurring (which needs to be tested) to map

Let the world know what's state the aircraft is in. We're upgrading from boring single LEDs to individually addressable WS2812B strips. Make a python module with different distinct visual modes to indicate device state

Finish creating Python module
mavlinkThread

Picking up and estimate the distance of the victim.

I've been looking into how to pick up bodies. I am assuming you've come across yolo
https://www.pyimagesearch.com/2018/11/12/yolo-object-detection-with-opencv/ and so far seems like a nice solution to me.

I've been testing it out on my laptop. It reliably analyses a single image in about 0.5 seconds and doesn't seem to be very intensive on my CPU (usually 1-2%) I'm not sure how this will relate to the Pi4 though.

Assuming this is a reasonable solution, I'm still unsure how to get it to recognise distance. I might be able to get it to pick up the size of the surrounding box and relate it's height with distance. Alternatively, maybe the real sense might be able to give some indication of the distance to the victim, though I don’t really know much about it.

If this is not a reasonable solution then, I'm not really sure of any other good methods that wouldn't be too intensive for the moment. Would be happy to try stuff out if you have suggestions.

(also if this is the wrong way to use the issues section, feel free to correct me)

https://stackoverflow.com/questions/17667903/python-socket-receive-large-amount-of-data

Should really package a requirements.txt file and virtual environment for simple setup

Implement the indoor location code

aircraft wobbles around and gets mighty confused

in navigation

def updatePt2(self, pointRisk):
    pathRisk = self.calculatePathRisk(self.gotoPoints, pointRisk)

    min_path_index = np.nanargmin(pathRisk)
    min_path_point = self.gotoPoints[min_path_index]
    min_path_risk = pathRisk[min_path_index]

min_path_index = np.nanargmin(pathRisk) this has a all nan slice error

I can't seem to figure out how to put/post successfully onto the smarthub I keep getting:
JSON schema validation error processing 'type' in: [] Details: { "expected": "object", "used": "null" }

I don't really understand the interfacing. I used their example at the bottom of https://docs.google.com/document/d/1JZiO76uum4PD-ZSnvFgsyPBroWn036L5v-G-_o4XG-0/edit# but when I try to apply what I think is similar logic, to the episode 12 interfaces, I just get that error.

no idea whats causing this, differences between set altitude, waypoint altitude, and ceiling altitude?

Computer Vision to find injured party

Provide instructions on setup for RPi and Ubuntu
JSB sim
Arducopter SITL

From risk map and target location generate GoTo location