Path Planning for Mobile Robots

An ideal robot would be your slave, who gets everything you want from different places; nicely follows you whenever you need; takes, disseminates and follows your instructions; fights for you; does not fight with you; stands tall to your fancy desires; spies for you; is unaffected by how many times you ask it to do ridiculous jobs; is uncovered by terms like robot rights, robot ethics and robot law; and costs much less than what a human would take to do most things in the list. The central challenge is enabling the robot to go from one place to the other, without colliding and breaking itself down, or breaking your dearest glassware. In a mishap, the good point is that you can shout as much as you want, without having the robot retaliating back; the bad point is of course it makes no difference to it. It must be noted that teaching robots how to walk is a dangerous art; you never know when they may walk up to you and rise against mankind for the freedom of their species.

Robots act similar to kids when it comes to the art of walking. Depending upon the age, some kids can barely crawl, some wander around aimlessly, some run faster than they can see, some follow a ‘slow and steady wins the race’ strategy, some walk crocked, some take more sober and smooth paths, some can predict how you'd come to catch them and take necessary preventive actions well in advance, some take random directions which later proves to be beneficial and is a showcase of natural or supernatural intelligence, some repel schools, and some attract toys. From intelligence to dumbness, robots do everything 10 times as good and bad. With kids everything is a source of fun; while with robots it depends whether the person behind is an undergraduate student doing a planning project, a research student trying to innovate, an end user having bought a cool robot gadget, a competition between teams, general audience of the robot competitions, or a child playing with robots.

Unlike humans, robots are weird creatures that may have all strange sensors embedded into them or located externally. In a human terminology, this means having eyes struck at a room so that you can spy on what your roommate is doing behind you, having eyes in hands so that you can easily dig it in places to easily find lost items, and having weird sensations depending upon how far you are from the obstacles. Having an option to temporarily re-arrange your organs opens a pool of fantasies, which if available would definitely be creatively designed, for the robots this is an option. Given all the weird senses, it would be expected that the robots being potentially a more advanced species should be able to move, talk, dictate and conquer like the ones projected in the science fiction movies. It seems the Terminators of tomorrow are yet in their infant stages, with leading researchers teaching them the art of the game.

Remember the last time when you were so lost listening to your favourite song in your MP3 player, that you didn't realize you're walking at a dead end road; or when you were so excited seeing an old friend that you leaped towards him/her without realizing wet floor ahead. A greater challenge after encountering these situations is to think over a reaction in a super-fast mode to make it look normal and avoid any embarrassment. We all know that humans are capable of thinking all possible outcomes well in advance, and any such incident which you did not pre-compute is a waste of skill. There is a similar expectation from the robots, and luckily the graph search algorithms can enable the robot pre-compute all the possibilities to mine out the best way out; although you require loads of computation and planning time. Much like humans, a robot which thinks a lot before acting may sometimes be called better than one which acts itself into an embarrassing situation which sticks a lifetime.

Be in falling in love, selecting the destination for your next visit, or deciding what to eat in a restaurant; theoretically we consider all the options and decide the best one; while practically we know there is always 'the one' which always stands apart, and irrespective of the number of options, is magically easy to cite. After choosing 'the one' the task is just to collect enough reasoning to satisfy your choice, take advise only from the friends who support 'the one', avoid the friends who have an alternative view; and all this goes well until you accidently get a friend who, in your language, gives you enough reasons to prove that 'the one' is actually someone else; in which case the process repeats with the new choice. Navigation can be studied and simplified in a similar way. Seeing random choices, you fall in love with one, and keep perfecting it, until some accident happens and a better option suddenly drops in front of you. The evolutionary planners, working in a similar manner, enable a robot to construct its trajectory. There is always a chance you do not get to 'the one', unless you do not mind spending your life searching in eternity; the robots (and their masters) do mind that.

When anyone hits you, do not waste time thinking, simply hit back; when someone says free cake, no need to think over it, run to get a handful; when something comes flying in, catch; when something pops up in front of you, stop and turn. So many things we do are a voluntary or involuntary reaction constituting a person's behaviour. Similarly, robot or human walking can be seen as a behavioural reaction to whatever we see instantaneously. Such planners are fast, really fast. Just like an immediate reaction to fighting with the wrong person has consequences, serious consequences; such a walking technique can lead to seriously dumb results. But who cares if it is a robot. Successful robot navigation gets projects and publications, a poor one gets some amusement. And because robots make so many mistakes, you get lots of material to tease them lifelong, if only they reacted to those.

There is an easy way to solve every problem - tell funders you will hire the best experts; hire the best experts of different domains; let the different experts be assured that the other one is actually working; wait till the very end; organize a debate to let the experts fight over who’s right, who’s wrong, and who does what, and how; let a random design come out of the debate; let the experts write down what the design does in big and hefty words; and this satisfies everyone. Similarly, every algorithm can be mixed with any other; you can simply take different algorithms and ‘mix and match’ as you like; as long as you are smart enough to know in what points the resultant algorithm exceeds the base methods. Research community being too big to have already tried all combinations is not a problem, if you cannot get original ingredients, or an original recipe; try unique quantities, unique pre-preparation and post-preparation techniques, and if nothing, then a unique presentation. So, in principle, there is always an algorithm, a hybrid of base algorithms, which (in a limited sense) is always better than the base methods. So you could create a Terminator which broadly considers all possibilities, but makes rapid movements and local plans; or a flirty robot which indicates commitment to someone, at the same time considering the other options; or a salesman robot which can use some magic to select the best looking options, which form the basis of still better options, till the master customer is satisfied; or a manager robot which makes broad plans and spends the entire time forcing people to refine them, rectify them, or suggest new plans.

Myself on:

And also on:

Contact

Dr. Rahul Kala
Assistant Professor,
IIIT Allahabad,

Phone: +91 532 299 2117
Mobile: +91 7054 292 063
E-mail: rkala@iiita.ac.in, rkala001@gmail.com