Comments (2)
Below we can see how obstacles are detected in simulation.
On the left terminal there's obstacleDetector
running, on the right the commands provided to navController
.
At the moment, the obstacle is a human model created here, since the actor we use for the demo is not seen by lasers (as described in #286). The human model is useful to see how legs are perceived by lasers
obstacleDetector
clusters the data received from the lasers, splitting them by means of a Euclidean distance. When the robot reaches a threshold distance (1.5m
) from the closest obstacle, obstacleDetector
sends a stop
to navController
. Only if the obstacle disappears, the robot can move again.
One obstacle in front of laser front
When starting, the obstacle is at 3m
in front of the robot.
obstacleDetector
detects two obstacles (the two legs), with the closest at ~2.9m
.
Note: the legs can be detected as a single obstacle or as two obstacles depending on the distance from the robot. The closer the robot, the more the legs are seen as two obstacles.
When sending the command to navController
for moving the robot at 5m
from the starting position along the x
, the distance from the obstacle starts decreasing and the robot stops when the distance threshold is reached (1.5m
).
When the obstacle is removed, obstacleDetector
does not detect any obstacle anymore and the robot is free to move.
One obstacle in front of laser back
This is the same scenario as before, with the obstacle being behind the robot and thus perceived by the back laser.
Several obstacles
In case of several obstacles, the robot stops when it approaches the closest.
obstacleDetector
detects 3 obstacles (2 legs from the closest and a single obstacle from the furthest) from laser front and 1 from laser back.
from assistive-rehab.
Super sweet 🚀
I've noticed how the legs are detected sometimes as 1 sometimes as 2 distinct obstacles. At this stage, we're not reconstructing the person entity from the laser detections so it's good 👍
As agreed, when the obstacle disappears, the supervisor will be responsible for driving the robot again toward the original target 👍
from assistive-rehab.
Related Issues (20)
- Remember to update CI for VCPKG Ports name HOT 1
- Update YARP portmonitor initialization HOT 5
- Use `depthimage_compression_zlib` pormonitor HOT 1
- Dependencies for cornerRefinementMethod HOT 2
- `lineDetector` and `skeletonRetriever` are to rely on I/F to get depth camera's params HOT 2
- CI fails because of `curl` build error HOT 4
- Setup and test the TUG demo on R1SN003 HOT 41
- Develop the connection Navigation ➡️ GRACE HOT 2
- Refine and test speech failure detection on R1SN003
- Host docker images on `ghcr.io/robotology` HOT 3
- Update kinematics for use with top camera
- Test the TUG metrics accuracy with and without human planes projection HOT 3
- Expose the available TUG metrics to the end user HOT 8
- Investigate the possibility to replace the Wi-Fi buttons HOT 3
- General upgrades to assistive-rehab docker image HOT 1
- Release `v0.8.0`
- Update website
- Improve the peak finding algorithm for gait estimation HOT 5
- Investigate possible race condition in `googleSpeech` module
- Improve handling of questions by `managerTUG` HOT 4
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from assistive-rehab.