Picking and Stowing in a Robotic Workflow

 Most interesting piece from IEEE, here is the intro. Made me think about similar tasks we examined. 

Stowing Is a “Beautiful Problem” That Amazon Is Solving With Robots Cramming items into warehouse pods takes clever new hardware    By Evan Ackerman

When we hear about manipulation robots in warehouses, it’s almost always in the context of picking. That is, about grasping a single item from a bin of items, and then dropping that item into a different bin, where it may go toward building a customer order. Picking a single item from a jumble of items can be tricky for robots (especially when the number of different items may be in the millions). While the problem’s certainly not solved, in a well-structured and optimized environment, robots are nevertheless still getting pretty good at this kind of thing.

Amazon has been on a path toward the kind of robots that can pick items since at least 2015, when the company sponsored the Amazon Picking Challenge at ICRA. And just a month ago, Amazon introduced Sparrow, which it describes as “the first robotic system in our warehouses that can detect, select, and handle individual products in our inventory.” What’s important to understand about Sparrow, however, is that like most practical and effective industrial robots, the system surrounding it is doing a lot of heavy lifting—Sparrow is being presented with very robot-friendly bins that makes its job far easier than it would be otherwise. This is not unique to Amazon, and in highly automated warehouses with robotic picking systems it’s typical to see bins that either include only identical items or have just a few different items to help the picking robot be successful.

Doing the picking task in reverse is called stowing, and it’s the way that items get into Amazon’s warehouse workflow in the first place.   .... ' 

Automated Workflows are Rolling

Clearly, and this will continue.   But doing it right will still be a challenge.  The advantage will be to those that use the best approaches, applied to context with the right AI and analytics.  Think Autonomous is the future. 

Automated workflows are eating the world  By Tristan Pollock in VentureBeat

In just the past 12 months, over $2.2 billion has been funneled into tech companies building workflow automation solutions. This isn’t a bubble. It’s a balloon.

Hot technology companies like Slack ($14.5 billion market cap), Calendly ($60 million ARR), Docusign ($36 billion market cap), GitHub (bought by Microsoft for $7.5 billion), and Airtable ($185 million Series D), all have built-in workflow builders that range from simplified code to low code to graphical no-code. All it takes is a matter of minutes plugging X to Y to Z.

Just days ago, Adobe purchased Workfront, a marketing workflow automation platform, for $1.5 billion. Before that, Apple purchased a startup called Workflow and turned it into the Apple Shortcuts app. Workflow automation is the future.  .... ' 

Consider the Flow, Tempo and Rhythm of Process

Had been looking at how different streams of work and delivery could be combined and transferred between  flows and tasks?    And had some time ago thought of the analogy of the combination of streams of music, rhythm, tempo and other musical measures and ideas.   Now discovered the Algoriddim system.   Could this be taken beyond music? Say to process flow and results?

Algoriddim’s Djay Pro AI can transfer vocals and rhythms between songs
JEREMY HORWITZ@HORWITZ JUNE 18, 2020 7:04 A

Algoriddim’s live DJ mixing and editing app — Djay Pro — has been a standout on iPads, iPhones, and Macs for years, enabling users to slow songs down, speed them up, scratch them, and blur them together with ease. Today, the company is evolving the iOS version of the app with AI features, using a trained neural network to transfer one song’s vocals or rhythms to another track in real time.

Djay Pro previously focused on synchronizing the speeds of two different tracks, rebalancing their volume levels or equalization and playing with each song as it “spun” on a virtual turntable. Algoriddim’s new Neural Mix feature goes deeper, isolating and pulling out vocals (a trick best suited to hip hop tracks) or percussive/harmonic components (ideal for electronic music). DJs can use the AI-powered feature to create background-free a cappella tracks or voice-free instrumentals from existing songs or place one song’s words on another’s background.  .... " 

Interaction Insights in Alexa Skills

This piece was published last year, but gave me some interesting insight recently about usage of skills.

Gain Interaction Insights Using New Analytics in the ASK Developer Console   By BJ Haberkorn

Today we added interaction path analysis to the Analytics tab on the Alexa Skills Kit (ASK) Developer Console. Interaction path analysis shows aggregate skill usage patterns in a visual format, including which intents your customers use, in what order. This enables you to verify if customers are using the skill as expected, and to identify interactions where customers become blocked or commonly exit the skill. You can use insights gained from interaction path analysis to make your flow more natural, fix errors, and address unmet customer needs.


(Note the Use of Sankey Diagrams)

View Interaction Paths over Multiple Time Intervals
As shown in the example below, interaction path analysis provides a visual representation of the flow of users from the invocation of your skill to subsequent intents. In this example, most customers moved from LaunchRequest to Intent1. A smaller segment invoked Intent2 instead. Interaction path analysis shows both custom intents and built-in intents, such as

Building Dashboards with Story and Flow

Nicely done 12 page pdf from Tableau on building Dashboards.

 ... Making Flow Happen:
How to Build Dashboards That Persuade, Inform and Engage

In data visualization, flow is crucial. Your audience should smoothly absorb and use the information in a dashboard without distractions or turbulence. Lack of flow means lack of communication, which  means failure.

Psychologist Mihaly Czikszentmihalyi has studied flow extensively. Czikszentmihalyi and other researchers have found that flow is correlated with happiness, creativity, and productivity. People experience flow when their skills are engaged and they’re being challenged just the right amount. The experience is not too challenging or too easy: flow is a just-right, Goldilocks state of being.

So how do you create flow for an audience? By tailoring the presentation of data to that audience. If you focus on the skills, motivations, and needs of an audience, you’ll have a better chance of creating a positive experience of flow with your dashboards. And by creating that flow, you’ll be able to persuade, inform, and engage. ... " 

Achieving a Flow State

Examined the ideas of psychologist Mihaly Csikszentmihalyi's  'Flow' way back. And now read a piece in medium by John Boitnott that points to work saying that multitasking is killing our brains.   Gives some ideas about achieving it.   Yes, need that protection with new devices popping up every day.  Also see the post on the 'Flow Game' tag below.

Global Digital Flows

From McKinsey

Digital globalization: The new era of global flows
By James Manyika, Susan Lund, Jacques Bughin, Jonathan Woetzel, Kalin Stamenov, and Dhruv Dhingra

Conventional wisdom says that globalization has stalled. But although the global goods trade has flattened and cross-border capital flows have declined sharply since 2008, globalization is not heading into reverse. Rather, it is entering a new phase defined by soaring flows of data and information.

Exploding digital flows in a deeply connected world ... Remarkably, digital flows—which were practically nonexistent just 15 years ago—now exert a larger impact on GDP growth than the centuries-old trade in goods, according to a new McKinsey Global Institute (MGI) report, Digital globalization: The new era of global flows. And although this shift makes it possible for companies to reach international markets with less capital-intensive business models, it poses new risks and policy challenges as well.  ... " 

Thoughts about the Essence of Flow

In InfoQ: A concept we worked with in the world of supply chain, but now it is useful in many more domains.   Well presented.   It is summarized:  " ... In this article I have talked about that all processes are constrained by bottlenecks. A common scenario in a software development company is that too much is going on at once, the work is too scattered and too thin. The relay baton in 4 x 100 meters Relay is a good example of flow. Finally a shift in mindset is described, to go from focus on resource efficiency to focus on flow efficiency and then some examples how to get flow are given. .. " 

Following Tableau 9 Beta

This week attended an overview of Tableau 9,0  Nicely done global streamed user meeting.  I have yet to try the Beta myself. Impression based on the presentation.

I much like the use of the phrase 'visual analytics'.   Visualization is analytics, and all analytics should start with visualization of data.

Overall they are basing their changes on the ability to establish 'Flow'  (The psychology theory of Mihály Csíkszentmihályi ) when analysing and visualizing the data.  Good idea, but this depends on the kind and needs of data and decisions being addressed.  I am all for easy of use via Flow.

Quite a few new ways to select data points on maps, which for certain kinds of analyses can be very useful.   The selection methods are quite intuitive.

Showed the integration of simple analytic, like regression based forecasting.  Easy to overlay on existing data.    Well done, but still a minimal amount of analytics.  When comparing it to other visualization packages like Spotfire.

I like very much what they have done with being able to derive level of detail (LOD) variables.  This is a very powerful concept, an excellent way to do some kinds of analysis, like Cohort methods.  But at the same time it takes you away from the purely visual interaction with data.  It is nice to know it is there, but it also gets you into the weeds of analysis.  The average non analytic user may be confused. They have a white paper coming on its value and use.  ( Will place link here ) Good

New kinds of data cleanup, meta data inclusion, ability to manipulate the data during its ingestion. Data that is strangely arranged or poorly pivoted in its original form. All good ideas that should prove useful.  Lots of times you just want to get the data in cleanly for ready use with a minimum of effort.

Look forward to getting my hands on this, which should be very soon.

Csikszentmihalyi's Flow Game

Learned about Mihaly Csikszentmihalyi's Flow Theory in a Sciam article about television addiction then tracked his work for some time, Flow " ... which holds that people are happy and fulfilled when they are fully immersed in what they are doing ... In short; flow could be described as a state where attention, motivation, and the situation meet, resulting in a kind of productive harmony or feedback ... "

Notably presented in his work: Flow: The Psychology of Optimal Experience and 1998 book Finding Flow: The Psychology of Engagement With Everyday Life. His ideas were naturally picked up by game designers.