#motionplanning

2024-04-15

Seeing some interesting path tree formations here!

( Variant of #rrt )

#pathplanning #motionplanning #robotics #research

A 3D rendering featuring a red sphere, as well as a set of red lines branching out from a central location, seemingly enveloping the red sphere.

There is a very notable hierarchy and branching nature to the paths, and they look relatively smooth.
2024-04-12

In order to test my motion-planning algorithms some more, I decided to try procedurally generating the arm of the robot, just to see how things would work under varying numbers and arragements of joints.

I then decided to render a quick animation of it.

...it works, but I can't help but think it looks inexplicably disturbing.

#robotics #motionplanning #pathplanning #video #animation #rendering #research

2024-04-09

Working to poke some fruit in an apple tree again with a simulated UAV equipped with a robotic arm.

Trying out a new way to visualize paths. In this case, the yellow path indicates a trace of the center of the flying base link, magenta follows the end-effector, with green connecting the two at simultaneous moments.

#robotics #uav #pathplanning #motionplanning #visualization #computerscience

3D rendering of a fruit tree carrying small red fruits. A long chain of lines along the outside of the tree shows a path that a robot might follow to reach the fruit.
2023-11-20

Playing around with some #inversekinematics

Here, the #robot was meant to keep the end-effector in the same place, while changing the joint angles to right the flying base.

Seems to work well enough!

#robot #robotics #kinematics #drone #quadcopter #motionplanning

Victor Paléologuepalaio@fediscience.org
2023-09-30

A well-rounded paper on how to translate symbolic statements into actionable constraints for #robotics control and #motionplanning: frontiersin.org/articles/10.33

In short: symbolic statements are produced by higher-level decision-making systems (e.g. from a #pddl planner working with #semanticmapping) and given to lower-level actions.

2023-07-28

# A fast two-stage approach for multi-goal path planning in a fruit tree

How do you efficiently plan a path for a drone around a fruit tree, and then plan its movements so it reaches into the tree to reach the fruit with a robotic arm? In what order do you do that?

It's my contribution to the 2023 International Conference on Robotics and Automation! #ICRA2023

ieeexplore.ieee.org/document/1

#conference #academia #publication #robotics #drones #UAV #motionplanning #pathplanning #roboticarm #algorithms #academia #research #ieee #ICRA #orchards #farming #agriculture

(Graphical abstract)

A FAST TWO-STAGE APPROACH FOR MULTI-GOAL PATH PLANNING IN A FRUIT TREE

An apple tree is depicted, with a circle around the canopy (cross section of a sphere), showing the fundamental gist of our technique. A drone is depicted on either side of the tree, with a path along the sphere illustrating how the sphere is uses to plan paths rapidly and efficiently.

University College Roosevelt logo in the bottom-left of the image.
Victor Paléologuepalaio@fediscience.org
2022-11-14

First time I encounter #stablediffusion used to perform #motionplanning: arxiv.org/pdf/2211.04604.pdf
They also translate natural language instructions #nlp into a set of goals (final poses of the end effector).
Nice #ai work.

2021-08-18

Boston Dynamics Atlas Dynamic Duo Tackles Obstacle Course

Historically, the capabilities of real world humanoid robots have trailed far behind their TV and movie counterparts. But roboticists kept pushing state of the art forward, and Boston Dynamics just shared a progress report: their research platform Atlas can now complete a two-robot parkour routine.

Watching the minute-long routine on YouTube (embedded after the break) shows movements more demanding than their dance to the song " Do You Love Me? " And according to Boston Dynamics, this new capability is actually even more impressive than it looks. Unlike earlier demonstrations, this routine used fewer preprogrammed motions that made up earlier dance performances. Atlas now makes more use of its onboard sensors to perceive its environment, and more of its onboard computing power to decide how to best move through the world on a case-by-case basis. It also needed to string individual actions together in a continuous sequence, something it had trouble doing earlier.

Such advances are hard to tell from a robot demonstration video, which are frequently edited and curated to show highlighted success and skip all the (many, many) fails along the way. Certainly Boston Dynamics did so themselves before, but this time it is accompanied by almost six minutes worth of behind-the-scenes footage. (Also after the break.) We see the robot stumbling as it learned, and the humans working to put them back on their feet.

Humanoid robot evolution has not always gone smoothly (sometimes entertainingly so) but Atlas is leaps and bounds over its predecessors like Honda Asimo. Such research finds its way to less humanoid looking robots like the Stretch. And who knows, maybe one day real robots will be like their TV and movie counterparts that have, for so long, been played by humans inside costumes.

[via Ars Technica]

#robotshacks #atlasrobot #bostondynamics #depthperception #legged #leggedlocomotion #motionplanning #parkour #perception #robot

image

Client Info

Server: https://mastodon.social
Version: 2025.04
Repository: https://github.com/cyevgeniy/lmst