Changan Chen

Hi @cherrymilk, I haven't seen this error before and it looks like some kind of memory error. Are you sure there are no other processes using too much memory and...

@hurong971013, the trajectory visualization code is here: https://github.com/vita-epfl/CrowdNav/blob/24be7ad39fed0658c5631c0820c67f9105e457bc/crowd_sim/envs/crowd_sim.py#L444-L484 and in the test.py, there are options to visualize the trajectory as well, which use the code above.

This fucntion currently directly plots the figure in a pop-up window, you need to add a line of code to save the figure to the desired location.

I just did a clean install and training/testing. Everything worked just fine. Please check if you modified any code that lead to this error. On Sun, Aug 22, 2021 at...

The number of pedestrians can be set to a random number in the training as well as in the test. To obtain the best testing performance, I think the number...

This is because we want the robot the take some more fine-grained actions when it gets close to the goal. Exponentially sampling leads to more low-valued velocities. We experimented with...

What kinda of computational cost? Do you mean training or test time? ORCRA does not need training and the rest are learning based. At test time, I think ORCA also...

hi @guldamkwak3114 we meant to normalize the scores alpha_i and do weighted sum of all h_i. Sorry for the bad and confusing writing.

Softmax is the normalization operation.

The softmax(alpha_i) here means doing softmax for all scores and take the ith component, which is just a single value. So we normalize the score with softmax for all neighbors...