Mistral's Robostral Navigate: a state of the art robotics navigation model

Join the discussion

• Hacker News
• Was it tested on a road in a car ?
  by maelito
• Relevant: https://blog.comma.ai/011release/
  by SparkyMcUnicorn
• Frontier labs are realizing that software/models themselves don’t have real moats and move to embodied ai.

  SOTA 80% means a practically useless robot. What are they really imagining their ICP to be here?

  by fzysingularity
• What does this comment mean?
  by not-kinsale-joe
• I love Uniqlo even more after seeing this.
  by infinito25
• Then today's your lucky day! https://news.ycombinator.com/item?id=48829312
  by sowbug
• How long until Tesla buys Mistral?
  by figassis
• I don't think so. I think Tesla merger with SpaceX, which has the Cursor team and reportedly working on foundation model there.

  I imagine the EU would block any attempted takeover of Mistral given recent Anthropic and US govt actions.

  by davidpapermill
• I'm ready for my home helper robot that makes dinner and does the dishes and takes out the trash.

  But I'm scared for when those home helpers get drafted to fight in wars, either for or against me...

  by montroser
• One intelligent humanoid robot per house. What could go wrong really. Possibly the worst idea.
  by stackbutterflow
• You should be relieved that they're sending robots instead of you to get blown up by a drone.
  by cbg0
• I think you'll be waiting a while for the former, unless you're ok with strangers teleoperating a robot around your house whenever it gets confused.
  by ainch
• I suspect the latter will come way before the former...
  by toyg
• No word on pricing or inference options i could see so not that interresting if it is not available to test.
  by gunalx
• Robots handle clean labs well; messy real‑world environments are still the real bottleneck.
  by skaiuijing
• Maybe their LLMs are not the best but design is top-notch!
  by heyheyhouhou
• 8B sounds tiny. Of course, that's enough to easily run on device which is nice, but surely the actual SOTA must be some much bigger model?
  by Tenoke
• Mistral seems to be going wide and niche. Could be a smart strategy going forward.
  by Gecko4072
• It's potentially a great strategy. They can't keep up with Antropic and OpenAI in pure horsepower, but there's just tons of applications for which you don't need that much power and it's better to optimize for speed and energy.
  by tootie
• For a claim such as state of the art, or claims such as "great at any task" needs something of more substance. I've seen maze-solving robot competitions which can zoom around in seconds. The sped up video in the first part, and the "obstacle avoidance" are too slow for me to believe this is state of the art.

  While impressive at 8B, what would the expectation be in real life, that it's run remotely or autonomously with a strapped on GPU and battery?

  by mhitza
• it is state of the art, those maze solving things are a different art.
  by nancyminusone
• Ok, this is really cool. The fact that the robot can use pointing to decide where to go is a great design decision, and robotics really is the next frontier. Definitely cheering on Mistral here!
  by ImageXav
• > achieves 76.6% on R2R-CE (Room-to-Room in Continuous Environments)

  I would like to know what it did the other 23.4% of the time!

  by mil22
• Random, horrendous and indiscriminate killing!

  [/joke]

  by marcusf
• Probably it achieved outside-from-outside in discrete void. Teleportation wasn’t an expected outcome for this experiment, but on the other hand the instructions didn’t forbid that kind of move.
  by psychoslave
• maybe it did a cartwheel instead of turning right.
  by dwa3592
• Presumably it did not make it to the other Room.
  by semiquaver
• "Go to the next room" and there is two doors, what do you do ?", "turn at the water dispenser" and there is a sink, that sort of things I assume is the biggest thing they're facing (beside the last 1% that's worth another 99%, as usual).

  On their page where the result graph is, go to navigation error, that's the one that matters for your question, and you see their model is great at not navigating "wrong", so their failure rate was that it couldn't figure it out.

  by nolok
• Funny how nearly all model improvements this year are demonstrated on the subset of use cases where brute force / reinforcement learning is most effective:

  Robotics (using physics sims)

  Cybersecurity (red team / blue team)

  Math (using automated proof checkers)

  Programming (using compilers)

  I’m not sure this inspires confidence in AGI arriving any time soon.

  by therobots927
• If you're wondering what prevents or mitigates AI hallucinations on the AI layer from replicating or acting out on the physical layer look up QNX. They manage the deterministic reasonin gof robotics. You know them better as Blackberry.
  by LurkandComment