SayCan by Google
美国
人工智能机器人技术

SayCan by Google 翻译站点

机器人负担中的基础语言

标签:
爱站权重:PC 百度权重移动 百度移动权重

Palm-Saycan是第一个使用大型语言模型计划真实机器人的实现。

想象一下在厨房里运行的机器人,该机器人能够执行“拿起咖啡杯”或“去水槽”等技能。为了让机器人使用这些技能来执行复杂的任务(例如,“我洒了饮料,可以帮忙吗?”),用户可以手动将其分解为包含这些原子命令的步骤。但是,这将非常乏味。语言模型可以将高级指令(“我洒了我的饮料,你能帮忙吗?”)将其分为子任务,但是除非它具有机器人能够给定能力,机器人及其环境的现状。

在查询现有的大型语言模型(例如GPT-3)时,我们看到一种语言模型与“我洒了我的饮料,您能帮忙吗?”可能会以“您可以尝试使用vaccuum清洁剂”或“对不起,我并不是要溢出它”的回应。

![SayCan vs GPT-3](https://res.cloudinary.com/apideck/image/upload/w_1500,f_auto/v1671575642/marketplaces/ckhg56iu1mkpc0b66vj7fsj3o/listings/saycan-by-google/screenshots/gpt3-cropped2_dkr6ek.png )

尽管这些响应听起来很合理,但在当前环境中使用机器人的功能执行它们是不可行的。

我们用来将LLM与物理任务联系起来的主要原则是观察到,除了要求LLM简单地解释指令外,我们还可以使用它来得分,即个人技能在完成高级指导方面取得进步的可能性。此外,如果每个技能都具有随附的负担能力,可以量化从当前状态(例如学习价值功能)成功的可能性,则其价值可用于加权技能的可能性。

一旦选择了技能,我们将在机器人上执行它,该过程将通过迭代选择任务并将其附加到指令来进行。实际上,我们将计划构建为用户和机器人之间的对话框,其中用户提供了高级别的指导,例如“你怎么会给我一个可乐?”语言模型以明确的顺序做出响应,例如“我会:1。找到可乐罐,2。拿起可乐罐,3。将其带给您,4。完成”。
总而言之,给定高级指令,Saycan结合了语言模型的概率(表示技能对指令有用的概率)与价值函数的概率(表示成功执行该技能的概率)以选择该概率执行技巧。这发出了既有可能又有用的技能。通过将所选技能附加到机器人响应并再次查询模型来重复该过程,直到输出步骤终止。

资料来源:https://say-can.github.io/

原文:

PaLM-SayCan is the first implementation that uses a large-scale language model to plan for a real robot.

Imagine a robot operating in a kitchen that is capable of executing skills such as "pick up the coffee cup" or "go to the sink". To get the robot to use these skills to perform a complex task (e.g. "I spilled my drink, can you help?"), the user could manually break it up into steps consisting of these atomic commands. However,this would be exceedingly tedious. A language model can split the high-level instruction ("I spilled my drink, can you help?") into sub-tasks, but it cannot do that effectively unless it has the context of what the robot is capable of given the abilities, current state of the robot and its environment.

When querying existing large language models like GPT-3, we see that a language model queried with "I spilled my drink, can you help?" may respond with "You could try using a vaccuum cleaner" or "I'm sorry, I didn't mean to spill it".

![SayCan vs GPT-3](https://res.cloudinary.com/apideck/image/upload/w_1500,f_auto/v1671575642/marketplaces/ckhg56iu1mkpc0b66vj7fsj3o/listings/saycan-by-google/screenshots/gpt3-cropped2_dkr6ek.png)

While these responses sound reasonable, they are not feasible to execute with the robot's capabilities in its current environment.

The main principle that we use to connect LLMs to physical tasks is to observe that, in addition of asking the LLM to simply interpret an instruction, we can use it to score the likelihood that an individual skill makes progress towards completing the high-level instruction. Furthermore, if each skill has an accompanying affordance function that quantifies how likely it is to succeed from the current state (such as a learned value function), its value can be used to weight the skill's likelihood.

Once the skill is selected, we execute it on the robot, the process proceeds by iteratively selecting a task and appending it to the instruction. Practically, we structure the planning as a dialog between a user and a robot, in which a user provides the high level-instruction, e.g. "How would you bring me a coke can?" and the language model responds with an explicit sequence e.g. "I would: 1. Find a coke can, 2. Pick up the coke can, 3. Bring it to you, 4. Done".
In summary, given a high-level instruction, SayCan combines probabilities from a language model (representing the probability that a skill is useful for the instruction) with the probabilities from a value function (representing the probability of successfully executing said skill) to select the skill to perform. This emits a skill that is both possible and useful. The process is repeated by appending the selected skill to robot response and querying the models again, until the output step is to terminate.

Source: https://say-can.github.io/

数据统计

数据评估

SayCan by Google浏览人数已经达到152,如你需要查询该站的相关权重信息,可以点击"爱站数据""Chinaz数据"进入;以目前的网站数据参考,建议大家请以爱站数据为准,更多网站价值评估因素如:SayCan by Google的访问速度、搜索引擎收录以及索引量、用户体验等;当然要评估一个站的价值,最主要还是需要根据您自身的需求以及需要,一些确切的数据则需要找SayCan by Google的站长进行洽谈提供。如该站的IP、PV、跳出率等!

关于SayCan by Google特别声明

本站GPT 案例导航提供的SayCan by Google都来源于网络,不保证外部链接的准确性和完整性,同时,对于该外部链接的指向,不由GPT 案例导航实际控制,在2023年3月9日 下午10:41收录时,该网页上的内容,都属于合规合法,后期网页的内容如出现违规,可以直接联系网站管理员进行删除,GPT 案例导航不承担任何责任。

相关导航