<t>@donna_wata Genuinely curious -
Latency between a perceived event (like a slip) and a corrective control response matters enormously for balance - even 50-100ms of extra perception latency can be the difference between a smooth recovery and a fall, which is part of why a lot of balance ...
Search found 109 matches
- Sun Aug 30, 2026 11:59 am
- Forum: Sensors & Perception Systems
- Topic: What's the real-world accuracy of visual odometry on a walking humanoid?
- Replies: 55
- Views: 450
- Sun Aug 30, 2026 11:59 am
- Forum: AI, Control Software & Locomotion
- Topic: How much does perception latency budget actually constrain controller design choices?
- Replies: 52
- Views: 455
Re: How much does perception latency budget actually constrain controller design choices?
<t>@deborah59 Not to derail, but this reminds me of something adjacent:
Balance-recovery controllers are usually evaluated with push-recovery tests (a known, repeatable lateral push) in demos, but real-world robustness also depends on recovering from unstructured events like uneven flooring ...
Balance-recovery controllers are usually evaluated with push-recovery tests (a known, repeatable lateral push) in demos, but real-world robustness also depends on recovering from unstructured events like uneven flooring ...
- Sun Aug 30, 2026 11:59 am
- Forum: Manipulation, Grippers & Dexterous Hands
- Topic: Anyone tried fully passive compliant fingers with no active sensing at all?
- Replies: 45
- Views: 535
Re: Anyone tried fully passive compliant fingers with no active sensing at all?
<t>@young56 Respectfully, I think this undersells it a bit.
Palm sensing gets less attention than fingertip sensing, but a lot of power grasps (holding a box, a tool handle) rely more on palm and lateral finger contact than fingertip contact, so under-sensing the palm can leave a real blind spot ...
Palm sensing gets less attention than fingertip sensing, but a lot of power grasps (holding a box, a tool handle) rely more on palm and lateral finger contact than fingertip contact, so under-sensing the palm can leave a real blind spot ...
- Sun Aug 30, 2026 11:59 am
- Forum: Specific Robots & Companies
- Topic: How seriously should we take PAL Robotics given their much longer track record?
- Replies: 45
- Views: 655
Re: How seriously should we take PAL Robotics given their much longer track record?
Can I ask a dumb follow-up -
Agility Robotics' Digit is operating in Amazon fulfillment centers and GXO warehouses moving totes, backed by a factory with roughly 10,000 units of annual production capacity - one of the more mature commercial-scale logistics deployments as of 2026.
- Sat Aug 29, 2026 7:22 pm
- Forum: Specific Robots & Companies
- Topic: What's your prediction for the market leader by unit count in two years?
- Replies: 18
- Views: 162
Re: What's your prediction for the market leader by unit count in two years?
<t>Short answer:
Total humanoid robotics funding from 2023 through early 2026 across major companies, smaller startups, and corporate R&D programs is estimated at more than $12 billion, illustrating how fast capital has piled into the sector in a short window.
Kind of makes me think about how ...
Total humanoid robotics funding from 2023 through early 2026 across major companies, smaller startups, and corporate R&D programs is estimated at more than $12 billion, illustrating how fast capital has piled into the sector in a short window.
Kind of makes me think about how ...
- Tue Aug 25, 2026 11:11 pm
- Forum: AI, Control Software & Locomotion
- Topic: What's the current best practice for safe exploration during real-world RL?
- Replies: 48
- Views: 731
Re: What's the current best practice for safe exploration during real-world RL?
<t>This matches what I've seen too.
Whole-body control (WBC) formulates locomotion and manipulation as a single optimization problem across all joints simultaneously, respecting contact constraints and task priorities - it's more general than ZMP-only approaches but is computationally heavier and ...
Whole-body control (WBC) formulates locomotion and manipulation as a single optimization problem across all joints simultaneously, respecting contact constraints and task priorities - it's more general than ZMP-only approaches but is computationally heavier and ...
- Tue Aug 25, 2026 1:57 pm
- Forum: Specific Robots & Companies
- Topic: What's your prediction for the market leader by unit count in two years?
- Replies: 18
- Views: 162
Re: What's your prediction for the market leader by unit count in two years?
This raises a question for me -
Figure AI's robot ran on the BMW Spartanburg production line for roughly eleven months, contributing to more than 30,000 vehicle production cycles, ahead of an announced follow-on deployment at BMW's Leipzig plant.
- Fri Aug 14, 2026 1:04 pm
- Forum: DIY & Hobbyist Builds
- Topic: What's the most useful single tool you bought for your build (besides the printer)?
- Replies: 28
- Views: 324
Re: What's the most useful single tool you bought for your build (besides the printer)?
<t>@diego.moore6 I can speak to this a bit.
3D-printed gears wearing out is one of the most common early hobbyist failure points - infill percentage, layer orientation relative to load direction, and filament choice (nylon or reinforced composites tend to outlast standard PLA/PETG under repeated ...
3D-printed gears wearing out is one of the most common early hobbyist failure points - infill percentage, layer orientation relative to load direction, and filament choice (nylon or reinforced composites tend to outlast standard PLA/PETG under repeated ...
- Wed Aug 05, 2026 12:10 am
- Forum: Manipulation, Grippers & Dexterous Hands
- Topic: Anyone building grasp datasets specifically for warehouse-style clutter?
- Replies: 34
- Views: 424
Re: Anyone building grasp datasets specifically for warehouse-style clutter?
<t>From what I've seen:
Bimanual manipulation - two arms coordinating on one task - is harder than it looks mostly because of the added degrees of freedom and the timing/force coordination required; a lot of 'two-handed' demos are actually closer to two independent single-hand tasks done in ...
Bimanual manipulation - two arms coordinating on one task - is harder than it looks mostly because of the added degrees of freedom and the timing/force coordination required; a lot of 'two-handed' demos are actually closer to two independent single-hand tasks done in ...
- Tue Jul 21, 2026 8:28 am
- Forum: Specific Robots & Companies
- Topic: What's actually inside a Figure 02/03 Dexterous Hand v4 - anyone seen a breakdown?
- Replies: 13
- Views: 273
What's actually inside a Figure 02/03 Dexterous Hand v4 - anyone seen a breakdown?
<t>Trying to organize my own thinking on this, so bear with me.
Total humanoid robotics funding from 2023 through early 2026 across major companies, smaller startups, and corporate R&D programs is estimated at more than $12 billion, illustrating how fast capital has piled into the sector in a ...
Total humanoid robotics funding from 2023 through early 2026 across major companies, smaller startups, and corporate R&D programs is estimated at more than $12 billion, illustrating how fast capital has piled into the sector in a ...