一些问题的总结

[Gutilence14]

1、AssertionError: Rendering dt (0.03333333333333333) must be a multiple of physics dt (0.01)
把config.yaml中的physics_frequency改成30
2、assert th.all(scale > 1e-4), f"Scale of {self.name} is too small: {scale}"
把og_scene_file_pen.json第897行的scale改成[2.0,2.0,2.0]
3、后续各种数据类型问题
把所有的Tensor改成numpy即可

我还遇到一个问题暂时无法解决，但是不影响使用
打开仿真器之前会报错无法链接到动态库，希望有缘人解答

[Bailey-24]

哈喽，哥们，我运行python main.py --use_cached_query，
但一开始笔会直接掉到桌子下面，你有遇到吗，怎么解决比较好。

[Gutilence14]

哈喽，哥们，我运行python main.py --use_cached_query， 但一开始笔会直接掉到桌子下面，你有遇到吗，怎么解决比较好。

没遇到这个问题，但是应该是场景初始化的坐标有问题，可以在那个json文件里的坐标随便改改试试

[Bailey-24]

嗯嗯，
json那里改成

            "pen_1": {
                "root_link": {
                    "pos": [
                        -0.30,
                        -0.15,
                        0.7163046002388
                    ],
                    "ori": [ -0.7071068, 0, 0, 0.7071068 ],
                    "lin_vel": [
                        0.0,
                        0.0,
                        0.0
                    ],
                    "ang_vel": [
                        0.0,
                        0.0,
                        0.0
                    ]
                },
                "joints": {},
                "non_kin": {}
            },

就好了

[Bailey-24]

知乎版，复现debug过程

https://zhuanlan.zhihu.com/p/945556099。

或者git clone https://github.com/Bailey-24/Rekep

[wzl1026]

你好，可以加您给联系方式吗，我和您有相同的问题，可以请教一下您吗

[coutendlsdsd]

知乎版，复现debug过程

https://zhuanlan.zhihu.com/p/945556099。

或者git clone https://github.com/Bailey-24/Rekep

Traceback (most recent call last):
File "E:\Rekep\main.py", line 379, in
main = Main(scene_file, visualize=args.visualize)
File "E:\Rekep\main.py", line 51, in init
self.subgoal_solver = SubgoalSolver(global_config['subgoal_solver'], ik_solver, self.env.reset_joint_pos)
File "E:\Rekep\subgoal_solver.py", line 124, in init
self._warmup()
File "E:\Rekep\subgoal_solver.py", line 134, in _warmup
self.solve(ee_pose, keypoints, keypoint_movable_mask, goal_constraints, path_constraints, sdf_voxels, collision_points, True, None, from_scratch=True)
File "E:\Rekep\subgoal_solver.py", line 253, in solve
opt_result = dual_annealing(
File "C:\Users\xiachenglei\miniconda3\envs\omnigibson\lib\site-packages\scipy_lib_util.py", line 440, in wrapper
return fun(*args, **kwargs)
File "C:\Users\xiachenglei\miniconda3\envs\omnigibson\lib\site-packages\scipy\optimize_dual_annealing.py", line 674, in dual_annealing
energy_state.reset(func_wrapper, rng_gen, x0)
File "C:\Users\xiachenglei\miniconda3\envs\omnigibson\lib\site-packages\scipy\optimize_dual_annealing.py", line 173, in reset
self.current_energy = func_wrapper.fun(self.current_location)
File "C:\Users\xiachenglei\miniconda3\envs\omnigibson\lib\site-packages\scipy\optimize_dual_annealing.py", line 381, in fun
return self.func(x, *self.args)
File "E:\Rekep\subgoal_solver.py", line 39, in objective
collision_cost = 0.8 * calculate_collision_cost(opt_pose_homo[None], sdf_func, collision_points_centered, 0.10)
File "E:\Rekep\utils.py", line 36, in calculate_collision_cost
transformed_pcs = batch_transform_points(collision_points, poses)
File "C:\Users\xiachenglei\miniconda3\envs\omnigibson\lib\site-packages\numba\core\dispatcher.py", line 442, in _compile_for_args
raise e
File "C:\Users\xiachenglei\miniconda3\envs\omnigibson\lib\site-packages\numba\core\dispatcher.py", line 375, in _compile_for_args
return_val = self.compile(tuple(argtypes))
File "C:\Users\xiachenglei\miniconda3\envs\omnigibson\lib\site-packages\numba\core\dispatcher.py", line 886, in compile
cres = self._cache.load_overload(sig, self.targetctx)
File "C:\Users\xiachenglei\miniconda3\envs\omnigibson\lib\site-packages\numba\core\caching.py", line 633, in load_overload
target_context.refresh()
File "C:\Users\xiachenglei\miniconda3\envs\omnigibson\lib\site-packages\numba\core\base.py", line 277, in refresh
self.typing_context.refresh()
File "C:\Users\xiachenglei\miniconda3\envs\omnigibson\lib\site-packages\numba\core\typing\context.py", line 158, in refresh
self.load_additional_registries()
File "C:\Users\xiachenglei\miniconda3\envs\omnigibson\lib\site-packages\numba\core\typing\context.py", line 745, in load_additional_registries
from . import (
File "C:\Users\xiachenglei\miniconda3\envs\omnigibson\lib\site-packages\numba\core\typing\cffi_utils.py", line 19, in
ffi = cffi.FFI()
File "c:/users/xiachenglei/miniconda3/envs/omnigibson/lib/site-packages/isaacsim/extscache/omni.kit.pip_archive/pip_prebundle/cffi/api.py", line 54, in init
raise Exception("Version mismatch: this is the 'cffi' package version %s, located in %r. When we import the top-level '_cffi_backend' extension module, we get version %s, located in %r. The two versions should be equal; check your installation." % (
Exception: Version mismatch: this is the 'cffi' package version 1.16.0, located in 'c:/users/xiachenglei/miniconda3/envs/omnigibson/lib/site-packages/isaacsim/extscache/omni.kit.pip_archive/pip_prebundle/cffi/api.py'. When we import the top-level '_cffi_backend' extension module, we get version 1.17.1, located in 'C:\Users\xiachenglei\miniconda3\envs\omnigibson\lib\site-packages\_cffi_backend.cp310-win_amd64.pyd'. The two versions should be equal; check your installation.

大佬，我是出现了这个问题想问下咋解决的