From e52ce31d1f9fa56d613c6ad159213c4f267ff4d0 Mon Sep 17 00:00:00 2001 From: Russ Tedrake Date: Sun, 6 Oct 2024 15:24:31 -0400 Subject: [PATCH] fix typos pointed out by annotations --- book/mobile.html | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/book/mobile.html b/book/mobile.html index 1609791d..9a48ba66 100644 --- a/book/mobile.html +++ b/book/mobile.html @@ -142,11 +142,11 @@

Robotic Manipulation< require explicit object models, that supports the types of queries we need for motion planning (for instance, fast collision detection and minimum-distance computations), which we can update efficiently from our - raw sensor data, and which scale well to large scenes. Raw, merged point + raw sensor data, and which scales well to large scenes. Raw, merged point clouds, for instance, are easy to update and don't require a model, but would not be ideal for fast planning queries.

-

Voxel grids are a geometry representation that meets (almost all of) the +

Voxel grids are a geometry representation that meets (almost all of) our desiderata -- we actually used them already in order to efficiently down-sample a point cloud. In this representation we discretize some finite volume of 3D space into a grid of fixed-size cubes; let's say 1 cm$^3.$ We @@ -156,7 +156,7 @@

Robotic Manipulation< geometry to be avoided. Many collision queries with voxel grids can be fast (and are easily parallelized). In particular the sphere-on-voxel collision query can be very fast, which is one of the reasons that you see a number - of collision geometries in the Drake models that are approximate with + of collision geometries in the Drake models that are approximated with densely packed spheres. Figure Updating a voxel grid with points clouds is also efficient. In order to scale voxel representations to have both fine resolution and to be able to represent very large scenes, we @@ -337,7 +337,7 @@

Robotic Manipulation<

When I've used the term "simulation" so far in these notes, I've been focusing mostly on the enabling technologies, like the physics engine and the - the rendering engine. In robotics today, there are only a handful of + rendering engine. In robotics today, there are only a handful of mainstream simulators which people are using, such as NVidia Isaac/Omniverse, MuJoCo, and Drake. (PyBullet was very popular but is no longer actively maintained.) But there is another crop of tools which call @@ -363,7 +363,7 @@

Robotic Manipulation<

Most of the ideas we've covered in this chapter so far can be considered relatively modest extensions to our existing manipulation toolbox. But there - are some important problem associated with navigating a mobile robot that + are some important problems associated with navigating a mobile robot that really don't come up in table-top manipulation.

Mapping (in addition to localization)