voice-over: this is bbc news. we'll have the headlines for you at the top of the hour, which is straight after this programme. this week, alasdair�*s looking to the skies for guidance... we're going to get some help navigating from up there. ..lara's getting hangry with a robot hand... no pressure, but i am quite hungry. i'm not sure how appealing that lettuce is looking after having that done to it. ..and spencer leaps forward to the year 2125.

i'm eye to eye with a cuttlefish. doesn't he need a snorkel for that?! mit's computer science and artificial intelligence laboratory is a world—leading facility, but today i've come to teach a thing or two — to the robots, that is, not the people — in a bid to help them behave as humanly as possible. especially with the tasks that we wouldn't give a second thought to. this reinforcement learning, where the machines mimic humans, is how the ai is trained. it aims to make the bots less, well, robotic and more multi—skilled. this motion is actually independent of where we place the glass and the pitcher, so we can have a much more adaptive system that does not need to have everything specified precisely.

in fact, this is part of the magic of machine learning. with machine learning, we can turn pre—programmed robots into intelligent machines. that means we can use data, we can use text, we can use images, we can even use muscle activity. and we can learn from this data how to do tasks in a much more seamless way. baxter's also been trained on doing the dishes and chopping veg — wouldn't that be nice? meanwhile — robotic hand, anyone? so, lara, this is another robot we've been working on. and what's special about the hand is that it's got a very compliant body, so it's got skin — in other words, soft material. can i touch it? you can touch it. it feels like silicone, but i can also feel what is like the bones inside. so the reason we put bones inside is because we want to have a hand that is compliant, and that's what we get from the silicone.

on with the glove, and time for a lighter task to start. my hands starting off in the same position as the bot, and the idea is that i'm going to train it to pick up that dollar bill. it's really sensitive to movement. as you can see here, just the tiniest turns and you can really see them. also, those movements are quite human. if i do a kind of typing action, look at that. look at the fingers in real time. right, so if i now move my hand down as though i'm going to pick up the dollar bill... 0k. you're off, you're off, you're off. you have to shift. i tried and failed repeatedly, so i'm not sure how much use

this training was. oh, so close! it's so frustrating! next up, a look at how robots can work as a team. think swarm of ants. what sort of real world uses would robotics created on this basis have? you could take a swarm of robots like these ones, and get them to go up a bridge to ensure the integrity of the bridge. we have to consider what should the body do, what should the brain do? and depending on the task of the robot, how should we design the body so that the body is capable of the task? but that's not enough. we then need the brain to get the body to do what it's meant to do. and i suppose the interaction between devices is really important for a real world purposes like self—driving cars, that they'd be able to see each other and understand how to interact with what's around them? exactly. so the coordination and group behaviour we get from local interactions to global behaviour are super important. that is part of physical

intelligence, that is part of getting robots to perceive the world around them and reason about it. and now it's turtle time. crush is autonomous, having learned to swim from data collected on real sea turtles. this actually gives us a very naturally moving robot that goes in the sea and does not disturb the sea life, and that allows us to study the sea life better. this robot is able to move whatever way we want in the sea, all of this enabled by its algorithms. i can actually see how natural the movement seems. the fact that it's not that even, it's smooth, but it doesn't seem that sort of organised in its movement, which is, of course, a very real way that a creature would behave. exactly.

from the seas to the skies, devices are not only learning from the physical world, but also from language and al's ability to reason. move towards the bag. this drone is being trained to understand instructions in any language. it's never seen a red bag or a traffic cone in its data set, but combining its understanding of language and vision, it is able to reason, so should be able to understand and carry out this command and so many more. and there it is — just by me instructing it in my own words, it ended up in the right spot. before i go, though, i have been promised some lunch. someone�*s making me a sandwich. no pressure, but i am quite hungry. i'm not sure how appealing that lettuce is looking after having that done to it.

it's not manhandled, it's robot—handled. it's getting there. turns out that, for robots, some of the jobs that we find the easiest are going to take some time to learn. it's like watching someone with a claw machine, just a really advanced version. and there we have it! i'm going to swim out to you in a couple of seconds. i'll grab you by your back and hold you tight. you sit there, 0k? alasdair: rough seas, high winds and flooding are just some extreme weather conditions this lifeboat crew must navigate. based on the south—west coast of scotland, the volunteers of nith inshore rescue are tasked with saving lives at sea — yes, even tam the dog. but the stretch of water where they launch the lifeboat, an estuary on the solway firth,

is exposed to rapidly moving tides. this creates tidal flats — basically sand and mud that move around. they're dangerous and difficult to map. it's the second biggest tidal range in the uk, and so when the tide is running, you can get a bore. so a wave will come in and literally salt flats, the mudflats and the sand gets covered very, very quickly. and that creates kind of a challenge around how we navigate out of this space, because it can lead to us not being able to get to where we need to at that critical moment. and with those tidal flats changing sometimes weekly, it's almost impossible to chart a safe route out to people in danger. but now, they've got a new tool to help them out. we're about to go out on the water with the crew, but when we're there, we're going to get some help navigating from up there.

orbiting above us, this is the european space agency's sentinel—2 mission. the satellites pass over the earth iii times a day, gathering a mix of data, including radar. it's then analysed by a team from strathclyde university to identify safe routes through the water. so what we've got here is a marine chart that shows us the area of the upper solway firth. if ijust zoom out a second, you'll see this whole white block. that's an area that basically means it's uncharted. and this is the area that you operate? this is the area we're operating. so that's a whole lot of sandbanks that are exposed when the tide are out. and although we can see a lot of water here, it's at a whole range of different depths. we'll shortly see the depth change, it'll change fairly dramatically. we go beyond the channel and it'll drop off as well. the low depth means the danger of the boat running aground is high.

traditionally, that means they've had to travel slowly to a rescue or relied on data gathered by hand, literally putting a stick in the water to see how deep it is. if i zoom in, these little red dots is the channel being marked. that's been generated by that satellite data. so the university of strathclyde have given us a whole load of waypoints in a file, and we literally just upload those into this, into this chart. you effectively get a sat nav for being out in the water? yeah. absolutely, yeah. lawrie, who is at the helm, has got a repeat of this screen so he can see what we can see here. before turning to space, the team tried using pictures from drones to see the tidal flats. but there is a problem — a day out on the water here is rarely as beautiful and clear as it is today. the problem that we have in the west of scotland in particular is that it is very cloudy, so you might occasionally get a cloud—free image, but they're really

unusual. so we're using radar data. radar penetrates through the cloud and it gives us much more frequent imagery of the area. but it's also much more complicated to process that data. and that was the real challenge that we had here. and so it is looking, effectively, at the ground and seeing where the sandbanks are? yes, it's looking at the, "where is the water? "where is the exposed sand and mud? "where is, kind of, the coastline?" and then if we can get images at low tide, then we can show the...where the water channel is, and then the crew can navigate through that water channel. to the naked eye, you can start to see it, but that's quite a manual process to actually just click and say, "well, go here." what we're doing is automate that so that you can then do it notjust here, but you could do it anywhere on any type of flat system. what the algorithm spits out is effectively latitude and longitude, and we then take those and create what's called a gps file. gps file goes into your garmin, goes into the navigation device on the boat so the crew

can load that directly onto their navigation device. for gwilym and the inshore rescue team, radar imagery is helping them to save lives at sea more safely and at speed. people locally and others who look at it, it's kind of a wizardry. it's kind of, like, a real magical thing that the first time we can go, "here's a set of waypoints "that recently have been captured," as a guide for navigation. it literally gives us a kind of an eye of what's under the water, you know, where the edges of that channel are, and that, for the first time, a confidence that we can head in a certain route.

are the cryptocurrency�*s are also making gains, bitcoin is a high risk investment asset and values can fall as well as increase. they have blocked messaging services like whatsapp, skype and facebook messenger on company devices in the uk. in a statement, they said that like many organisations, we only permit the use of approved channels for communicating about business matters. mobile operator has created an ai granny to waste the time of phone scammers stop it will keep scammers busy, tricking them that they are talking to a real person. them that they are talking to a real person-— them that they are talking to a real person. while they present talkinu real person. while they present talkin: to real person. while they present talking to me. _ real person. while they present talking to me, the _ real person. while they present talking to me, the camp - real person. while they present talking to me, the camp is - talking to me, the camp is coming you and let's face it, dear, i've got all the time in the world. dear, i've got all the time in the world-—

the world. the aim is to prevent _ the world. the aim is to prevent real _ the world. the aim is to prevent real victims - the world. the aim is to l prevent real victims being targeted while the vote can help give insight into common tactics that scammers use. there is a lot of seaweed in our oceans, and it's spreading fast because of climate change. it smothers coastlines around the world, disrupting tourism, fisheries and transport. but some scientists think it could be used as a natural resource to manufacture goods in a sustainable way. well, we visited a lab in norway which is working on a new method to make antibiotics by training bacteria to eat seaweed. seaweed is a big part of the world. we would like to use this species as food for bacteria to produce as antibiotics,

vitamins, any food ingredient you can think about. what we would like to do is to use cell factories. it's a bacteria that became expert on consuming sugars and producing antibiotics or vitamins. cell factories today mainly consume glucose—based biomass, which is, for example, sugar canes. in many places they grow huge amount of sugar cane, which cause deforestation. since this biomass is so abundant all over the planet, the idea is to try to use this instead of the food—based glucose. but these cell factories were not evolved to eat these sugars. we will need to teach the bacteria — or to engineer it — to consume these sugars, otherwise it will not grow. this lab is about investigating how to optimally grow bacteria. we are developing all

the software ourselves. artificial intelligence, algorithms, the machine learning, it's all custom made in—house. the seaweed is taken by the companies. they use high pressure and temperature to break down the seaweed into the sugar molecules. so we are now studying how we can feed these into the bacteria, and how the bacteria reacts to it. this is a vessel, you see, where the bacteria grows. it's fully maintained automatically — temperature, the acidity, the oxygen level. if we change any of the conditions, it immediately reacts. we study how it reacts and how it produces the molecule we want. so a sample is taken from the reactor because we want to analyse and understand how much antibiotics it's producing, or how much

sugar it consumes. ideally, we want the bacteria to consume all the sugars and then to grow and produce what it needs to produce. we have algorithms that understand what's happened to the model, and then do calculations on what the bacteria needs. it feeds the bacteria, it keeps it alive. now the challenge is reduced to how to optimise it. there is a big amount of seaweed everywhere, from india to indonesia. it can create jobs for farmers, and they do grow it today, but the value of this is very, very low. once we make it a valuable material for fermentation, new ones will appear in countries that don't have so manyjobs. deep in the heart of london's natural history museum, the exhibits are coming to life. i'm surrounded by fireflies. oh, wow!

visions of nature takes visitors to the year 2125 to see how the natural world is adapting to climate change and human behaviour. when people think about museums, they often associate them with the past, maybe the present. the great thing about this exhibition and this experience is it gives us a chance to talk about the future, and to present a view of the future. we've worked really, really closely with the museum scientists to make sure that that future is credible and is based on a scientific, rigorous process. and whilst none of us know what's going to happen in the future — you know, these are imagined scenarios — but they are scenarios based on current science, current thinking about what the really big challenges facing the planet are, but also what the most beneficial actions to try and address them are.

i'm eye—to—eye with a cuttlefish. this is a mixed reality experience. some of the exhibition is physically here, but the real stars come out when you look through microsoft's hololens 2 headset. the great thing about using technology in this way is that it allows you to encounter nature and encounter these species in a way that most of us, to be honest, are probably quite unlikely to experience in our lives. but by giving people the chance to encounter nature in that way, hopefully it can encourage us even more to think about the sort of positive actions that we can take. there are eight ecosystems to explore, from the scottish highlands to the deepest oceans. i'm just about to free this giant coconut crab from a bit of plastic that it's got tangled in. yes! there we go. result.

the coconut crab is the world's largest terrestrial invertebrate. what that means is although they're born and they grow up in the water, they then move to land, and adult crabs can't actually swim and they can't go back into the ocean. it's a weird quirk of evolution. they're also absolutely enormous, and apparently their pincers are strong enough that they can crack coconuts. so i'm going to stay out of the way of this guy. scientists don't know exactly how animals may adapt and change in the next 100 years, but this exhibition illustrates likely scenarios. for example, as waters warm, belugas and narwhals may move into the same environments and interbreed, producing new offspring called narlugas. scientists were also asked to predict what might happen to these strange creatures. now, here comes a colugo.

colugo is known as a flying lemur, but they don't fly, and they're not lemurs, so... they're a very unusual mammal. they're sort of out there on their own. so, colugos normally prefer dense forest, and they have to have trees relatively closely spaced together in order to be able to move about, because they glide, not fly, and they need to be able to get up to a certain height and then use that height and do a long glide. and the idea is that as deforestation carries on, there will be less and less trees and they'll be further apart. and also, potentially, trees won't be as tall, but they can, in theory, glide tens and potentially up to 100m or more. so the idea is that some of them that are better at gliding could survive in the future with less forest. this is the other beautiful thing about the hololens — it can recognise your hands, so when you put them out, you can interact. ijust had a firefly

land on my finger. the device we're using, the hololens, has a lot of sensors. and what we love is the technology. actually, you can interact with the headset itself with your fingers. so we try to design some action from the visitors that are linked to their action, because when you act on something, you are into the story. and when you interact, you have an impact. and that's what we want to do with that technology, to have the visitor have an impact on the story. i think if you really want to enjoy a mixed reality experience, you have to be a bit forgiving, because the technology is still evolving. for example, the images don't go right the way to the edge of your vision, they're kind of in these smallish windows in the centre of what you can see, so sometimes an animal might drop off out of this rectangle. but if you can get over that, it is a really immersive experience. as you turn your head, as you move around, all the creatures stay absolutely locked in the sd space they're supposed to be

in, and it is an immersive experience. hello! i was quite surprised at how hopeful this experience is. i was expecting to put on this headset and see that the world of 2125 is just armageddon. but actually, what this tells you is that, yes, things are getting worse, but if we start to take action now, in 100 years' time, we could have improved things. the world will look different, species will have reacted in different ways, but we may very well be able to pull things back from the brink. we've really consciously tried to project a hopeful message around it. it's really easy to feel disempowered by the sheer scale of the crisis that the planet and the natural world is facing. and that can sometimes translate into apathy, actually, because itjust feels too big a problem to be able to do anything about. what we've really tried to do with this exhibition is show

that there are positive actions that we can take. and that's it from us here at the natural history museum in london, a place that doesn't just have spectacular views of the past, but also some pretty encouraging views of the future too. from me and hope, the blue whale, thanks for watching and we'll see you soon. hello! friday is another cold day coming up with a chance of seeing some further localised disruption. now, over recent hours we've seen very heavy snow showers push into north west england and across the northwest midlands, north wales too. and upstream these very bright clouds, that's the trough bringing extra heavy showers across the irish sea.

they're going to be working into cheshire, parts of greater manchester, the north—west midlands, north wales too. some communities could see five centimetres of snow. wouldn't be surprised if one or two areas got closer to ten, where those showers tend to merge together to give some longer spells of snow. a cold start to friday, with a risk of icy stretches just about anywhere. you might even see a bit of snow on the ground around the chilterns, the greater london area, if those showers make it across the midlands. as we go through friday, many of the showers will tend to revert back to rain or sleet, and they'll tend to be draped around coastal areas, leaving many inland parts of the uk dry with plenty of sunshine. but it's another very cold day, temperatures for many are around four to six celsius into the weekend we've got big problems thanks to this storm, bert. now this is going to be bringing multiple hazards to the uk friday night, as this rain bumps into the cold air, we could see a spell of snow, even at low levels,

just about anywhere. it will turn back to rain in most cases. however, the met office have already issued an amber weather warning for the high ground of scotland. ten to 20cm here, some of the higher hills could see double that up to 40cm. and it's a similar story for the high ground of northern england. transport disruption, power cuts are possible. further west we've got very strong winds, gusts of around 60 or 70 miles an hour around our irish sea coast, and huge amounts of rain build up this weekend, particularly around the hills and coasts in the west, and especially for wales and south—west england, where some of the high ground could pick up as much as 150mm of rain, bringing a significant risk of some flooding. if this continues to be indicated in our computer models, those yellow warnings could be upgraded to amber weather warnings. there will be a very slow rise in temperatures. eventually it will turn milder across western areas. on sunday, but still bringing very strong winds with severe gales across the north—west of the uk. heavy rain across southern counties of england. blustery showers elsewhere, but it looks like bert will be bringing milder weather but a significant risk of disruption around

this weekend.

welcome to newsday, reporting live from singapore. vladimir putin threatens any country supplying long—range missiles to ukraine as he flexes his muscles, launching a new intermediate—range ballistic missile at targets in ukraine. the international criminal court issues arrest warrants for israeli prime minister benjamin netanyahu and his former defence minister yoav gallant, as well as a hamas leader, citing criminal responsibility for alleged war crimes. and after much controversy, former congressman matt gaetz withdraws as donald trumps nominee for us attorney general forcing the president—elect to make a new pick.