Re:Robotic Motion Planning in Real-Time
by iandanforth on Tuesday June 21, 2016 @02:36AM
(#11943891)
This could be very very useful. A 7 DOF arm operating in an unconstrained space is a seriously intensive task to plan. The only concern I have for them as a company is if rnn based learning catches up quickly to the much more established search based planning. If they had a standard pci board we could test tomorrow that worked with a URDF and a stream of depth data, we'd almost certainly request one.
[ Parent
| on HN ]
It does indeed work off of URDFs and streamed sensor data right now. I'd recommend contacting Sean they might be able to accomodate your request.
Re:Robotic Motion Planning in Real-Time
by choosername on Tuesday June 21, 2016 @05:37AM
(#11944582)
RNNs with their inexplicable output are impossible to justify in case something goes wrong. I'm not sure how secure their reliabilty is.
Re:Robotic Motion Planning in Real-Time
by ericlavigne on Tuesday June 21, 2016 @10:19PM
(#11951130)
Finding an optimal solution is much more computationally intensive than verifying that the solution is good enough (no collisions). If you don't really trust the RNN's work, then you can use a second algorithm just to check for collisions in the proposed plan.