BatchRenderer#

BatchRenderer 提供高吞吐量的并行渲染，针对大规模强化学习训练中的许多并行环境进行优化。

概述#

BatchRenderer 专为以下场景设计：

  • 最大吞吐量：针对渲染数千个环境进行优化

  • 并行执行：原生支持批处理仿真

  • RL 训练：高效的策略学习观测生成

  • GPU 加速：完整的 GPU 流水线，最小化 CPU 开销

快速开始#

import genesis as gs

gs.init()

# 创建具有多个环境的场景
scene = gs.Scene()
scene.add_entity(gs.morphs.Plane())
robot = scene.add_entity(gs.morphs.URDF(file="robot.urdf"))

# 使用并行环境构建
scene.build(n_envs=1024)

# 添加 batch renderer 相机
cam = scene.add_camera(
    res=(84, 84),
    pos=(2, 0, 1),
    lookat=(0, 0, 0.5),
)

# 训练循环
for step in range(10000):
    # 获取批处理观测
    obs = cam.render(rgb=True)  # 形状：(n_envs, H, W, 3)

    # 策略推理...
    actions = policy(obs)

    # 执行所有环境步骤
    scene.step()

配置#

通过 BatchRendererOptions 配置 BatchRenderer：

batch_options = gs.options.BatchRendererOptions(
    # 配置选项
)

输出格式#

当 n_envs > 1 时，相机输出是批处理的：

输出

形状

描述

rgb

(n_envs, H, W, 3)

批处理 RGB 图像

depth

(n_envs, H, W)

批处理深度图

segmentation

(n_envs, H, W)

批处理分割

性能提示#

  1. 分辨率：对于 RL 使用较小的分辨率（64x64 或 84x84）

  2. 渲染频率：仅在需要时渲染，而不是每步都渲染

  3. GPU 内存：监控使用大量环境时的显存使用

API 参考#

class genesis.vis.batch_renderer.BatchRenderer(visualizer, renderer_options, vis_options)[source]#

Bases: RBC

This class is used to manage batch rendering

add_light(pos, dir, color, intensity, directional, castshadow, cutoff, attenuation)[source]#
build()[source]#

Build all cameras in the batch and initialize Moderona renderer

update_scene(force_render: bool = False)[source]#
render(rgb=True, depth=False, segmentation=False, normal=False, antialiasing=False, force_render=False)[source]#

Render all cameras in the batch.

Parameters:

  • rgb (bool, optional) – Whether to render the rgb image.

  • depth (bool, optional) – Whether to render the depth image.

  • segmentation (bool, optional) – Whether to render the segmentation image.

  • normal (bool, optional) – Whether to render the normal image.

  • antialiasing (bool, optional) – Whether to apply anti-aliasing.

  • force_render (bool, optional) – Whether to force render the scene.

Returns:

  • rgb_arr (tuple of arrays) – The sequence of rgb images associated with each camera.

  • depth_arr (tuple of arrays) – The sequence of depth images associated with each camera.

  • segmentation_arr (tuple of arrays) – The sequence of segmentation images associated with each camera.

  • normal_arr (tuple of arrays) – The sequence of normal images associated with each camera.

colorize_seg_idxc_arr(seg_idxc_arr)[source]#
destroy()[source]#
reset()[source]#
property lights#
property cameras#
property seg_idxc_map#

另请参阅#