horizon of locomotion's pretrained model

[lch806376525-sketch]

Sorry to bother you.
In the pretrained model provided in the locomotion branch, the horizon of the diffusion model （defaults_T32_T20） and the value model （defaults_H32_T20_d0.997） are still the same as that of the diffuser's horizon=32. However, since you set horizon to 600 in config.locomotion.py, it seems that the model cannot be loaded correctly.
I can set horizon in config.locomotion.py to 32, and use the model provided by you to perform planning correctly. However, a trajectory based on horizon=32 is too short to produce the visualized plots shown in the paper, which were likely generated using horizon=600.
Could you please check the provided pretrained model, or let me know if my understanding is incorrect? If models trained with horizon=600 are available, could you share them?
I would appreciate your guidance. Thank you for your time and support!

[Weixy21]

The pretrained models are from the diffuser work. Unless they have changed the models, the default horizon is 600. Anyway, you may train the diffusion model and value model by yourself, and it won't take much time.

[lch806376525-sketch]

Thank you for your reply. I checked the locomotion branch of the diffuser project, and the horizon setting is indeed 32. I suspect you set the horizon to 600 to obtain the visualization image of the longer-horizon trajectory (Figure 3), is that correct?

Furthermore, I also noticed that you modified the max_episode_length to 500 (it is 1000 in the original diffuser project). So, which max_episode_length were used to calculate the SCORE and other data in Table 3: Robot safe planning comparisons with benchmarks? Thank you for the clarification. Meanwhile, is the diffusion model used to obtain these data using the horizon=32 diffusion model or the modified 600 diffusion model.

Besides, in the locomotion branch's ROS diffuser, why is the robustness term of 0.01 not included in the CBF (i.e., b = height - x[:,6:7] # - 0.1*x[:,15:16] # - 0.01 # for robustness)? Shouldn't this robustness term be necessary to ensure the effectiveness of the ROS diffuser? Your ROS related codes are as follows:
`@torch.no_grad() #only for sampling
def invariance(self, x, xp1): # RoS diffuser

    x = x.squeeze(0)
    xp1 = xp1.squeeze(0)

    nBatch = x.shape[0]
    ref = xp1 - x

    #normalize obstacle: Gaussian, x:0-6 control, 6-23 state
    height = 1.3
    height = (height - self.mean[0]) / self.std[0]

    #CBF
    ############################################ceiling
    b = height - x[:,6:7] # - 0.1*x[:,15:16]   # - 0.01  # for robustness
    Lfb = 0 
    Lgbu1 = -1*torch.ones_like(x[:,6:7])
    #Lgbu2 = -0.1*torch.ones_like(x[:,6:7])

    G = torch.cat([-Lgbu1], dim = 1)
    G = G.unsqueeze(1)
    k = 1
    h = Lfb + k*b
    

    q = -torch.cat([ref[:,6:7]], dim = 1).to(G.device)  #, ref[:,15:16]
    Q = Variable(torch.eye(1))
    Q = Q.unsqueeze(0).expand(nBatch, 1, 1).to(G.device)
    
    e = Variable(torch.Tensor())
    out = QPFunction(verbose=-1, solver = QPSolvers.PDIPM_BATCHED)(Q, q, G, h, e, e)

    rt = xp1.clone()      
    rt[:,6:7] = x[:,6:7] + out[:,0:1]
    # rt[:,15:16] = x[:,15:16] + out[:,1:2]
    # print(out[0:4,0:1])
    rt = rt.unsqueeze(0)
    return rt, torch.min(b)  # + 0.01  # for robustness`

Thank you once again for your guidance.