Samsung's Bespoke update is big step towards a useful AI for your fridge Samsung's Bespoke update is big step towards a useful AI for your fridge The idea of installing a software update on your fridge already feels kind of weird, let alone one centered around improving its AI capabilities. But that's exactly what's happening to Samsung's line of Bespoke refrigerators this week, and to my surprise this patch is making major strides at providing truly useful machine learning in a modern day icebox. As a quick recap, Samsung has offered AI-powered features like automatic food recognition and meal planning on its Bespoke refrigerators for a couple years already. However, as I found out after reviewing its flagship model late last year, the company's AI capabilities are still very much a work in progress. Previously, the fridge could recognize around 60 different kinds of fresh foods (like fruits and veggies) alongside another 50 or so packaged goods like yogurt or popcorn.

A.1 Dataset Details The 20 micro-variations of the 5 macro-variations of the scene were created with the rule of swapping at least two furniture pieces and perturbing the positions of a subset of the other furniture pieces. The occurrences of various furniture objects in these 100 micro-variations are illustrated in Figure 1. Several furniture objects such as'Beanbag' and'Chair' occur more frequently with multiple instances in a some scenes while others such as'Table 03' occur less frequently. We also analyze the object categories of all objects in the original 6 'FRL-apartment' space recreations. We map each of the 92 objects to a semantic category and list the counts per semantic category in a histogram in Figure 1. Since these spaces have a large kitchen area, there is a larger ratio of kitchen objects such as'Kitchen utensil' and'Bowl'. Top down views of the 5 'macro variations' of the scenes are shown in Figure 1. These variations are 5 semantically plausible configurations of furniture in the space generated by a 3D artist. Each surface is annotated with a bounding box, enabling procedural placement of objects on the surfaces. For each of these 5 variations, we generate 20 additional variations, giving 105 scene layouts. Objects are procedurally added on furniture and surfaces using the annotated supporting surface and containment volume information provided by ReplicaCAD.

We introduce Habitat 2.0 (H2.0), a simulation platform for training virtual robots in interactive 3D environments and complex physics-enabled scenarios. We make comprehensive contributions to all levels of the embodied AI stack - data, simulation, and benchmark tasks.

A.1 List of objects, containers, surfaces, and rooms in the apartment We list all the objects that are included in our experimental environment. We use the object rearrangement tasks for evaluation. The tasks are randomly sampled from different distributions. Simple: this task is to move one object in the house to the desired location. Novel Simple: this task is to move one object in the house to the desired location.