<t>One nitpick -
Imitation learning from human demonstration video (without robot teleoperation data) is an appealing way to scale up training data cheaply, but it runs into the embodiment gap - human hand kinematics and force profiles don't map directly onto a robot hand's very different ...
Search found 60 matches
- Sun Aug 30, 2026 11:59 am
- Forum: Manipulation, Grippers & Dexterous Hands
- Topic: How do people prototype hand mechanisms cheaply before committing to a final design?
- Replies: 19
- Views: 342
- Sun Aug 30, 2026 11:59 am
- Forum: Power Systems & Thermal Management
- Topic: Anyone else surprised how much runtime varies between 'static' and 'dynamic' tasks?
- Replies: 28
- Views: 412
Re: Anyone else surprised how much runtime varies between 'static' and 'dynamic' tasks?
<t>@vyoung Can I ask a dumb follow-up -
Hot-swappable battery packs solve the runtime bottleneck for continuous operations (like a 24/7 warehouse shift) without needing a much bigger, heavier pack, but they add mechanical complexity, a failure-prone connector interface, and logistics overhead for ...
Hot-swappable battery packs solve the runtime bottleneck for continuous operations (like a 24/7 warehouse shift) without needing a much bigger, heavier pack, but they add mechanical complexity, a failure-prone connector interface, and logistics overhead for ...
- Sun Aug 30, 2026 11:59 am
- Forum: Power Systems & Thermal Management
- Topic: What's the realistic near-term ceiling for runtime before the next real chemistry breakthrough?
- Replies: 29
- Views: 433
Re: What's the realistic near-term ceiling for runtime before the next real chemistry breakthrough?
<t>@klewis Just to be precise about one thing:
Idle/standing power draw is often surprisingly close to a meaningful fraction of active walking power draw once you account for onboard compute, sensors, and balance-holding torque - 'doing nothing' still costs real energy on a humanoid. There's no ...
Idle/standing power draw is often surprisingly close to a meaningful fraction of active walking power draw once you account for onboard compute, sensors, and balance-holding torque - 'doing nothing' still costs real energy on a humanoid. There's no ...
- Sun Aug 30, 2026 11:59 am
- Forum: Specific Robots & Companies
- Topic: How much should we trust company-published uptime and reliability stats?
- Replies: 16
- Views: 267
Re: How much should we trust company-published uptime and reliability stats?
<t>Genuinely curious -
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. Estimated total operational commercial humanoids worldwide ...
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. Estimated total operational commercial humanoids worldwide ...
- Sun Aug 30, 2026 11:59 am
- Forum: DIY & Hobbyist Builds
- Topic: Anyone attempted a fully open-source dexterous hand build?
- Replies: 22
- Views: 242
Re: Anyone attempted a fully open-source dexterous hand build?
<t>Pretty much this. One thing to add:
A lot of hobbyists underestimate how much of the real difficulty in a DIY humanoid build is software and tuning rather than mechanical assembly - getting a robot to physically stand up is a much smaller fraction of the total project time than getting it to ...
A lot of hobbyists underestimate how much of the real difficulty in a DIY humanoid build is software and tuning rather than mechanical assembly - getting a robot to physically stand up is a much smaller fraction of the total project time than getting it to ...
- Sun Aug 30, 2026 11:59 am
- Forum: Actuators, Motors & Drivetrains
- Topic: How do you even quantify 'feel' when comparing two actuators?
- Replies: 42
- Views: 483
Re: How do you even quantify 'feel' when comparing two actuators?
<t>@brenda52 One nitpick -
Torque sensing is frequently integrated directly into the actuator housing via strain gauges near the output flange or spring element, rather than bolted on as an external sensor, to save weight and reduce noise from mechanical slop. Harmonic drives use high reduction ...
Torque sensing is frequently integrated directly into the actuator housing via strain gauges near the output flange or spring element, rather than bolted on as an external sensor, to save weight and reduce noise from mechanical slop. Harmonic drives use high reduction ...
- Sun Aug 30, 2026 11:59 am
- Forum: Manipulation, Grippers & Dexterous Hands
- Topic: How do you handle grasping objects heavier than the rated payload safely?
- Replies: 50
- Views: 607
Re: How do you handle grasping objects heavier than the rated payload safely?
<t>@carol.robinson Can I ask a dumb follow-up -
Vision-based grasp confidence estimation (predicting success before attempting a grasp) and tactile-based confirmation (confirming after contact) are complementary rather than competing - vision helps you choose a grasp, tactile tells you if it ...
Vision-based grasp confidence estimation (predicting success before attempting a grasp) and tactile-based confirmation (confirming after contact) are complementary rather than competing - vision helps you choose a grasp, tactile tells you if it ...
- Sun Aug 30, 2026 11:59 am
- Forum: DIY & Hobbyist Builds
- Topic: Anyone built custom PCBs for motor control instead of buying drivers?
- Replies: 27
- Views: 241
Re: Anyone built custom PCBs for motor control instead of buying drivers?
<t>@novikova63 +1 to this. Worth adding:
Off-the-shelf RC servos are a reasonable starting point for a first small biped because they bundle motor, gearbox, and basic position control in one part, but they generally can't deliver the torque density or backdrivability needed to scale up to a ...
Off-the-shelf RC servos are a reasonable starting point for a first small biped because they bundle motor, gearbox, and basic position control in one part, but they generally can't deliver the torque density or backdrivability needed to scale up to a ...
- Sun Aug 30, 2026 11:59 am
- Forum: Careers, Research & Academia
- Topic: Anyone gone the other direction - robotics industry back into pure software roles?
- Replies: 50
- Views: 801
Re: Anyone gone the other direction - robotics industry back into pure software roles?
<t>@nancy_lewi I'll believe the stronger version of that claim when it's independently verified.
Robotics engineers in the US were reportedly seeing $150k-$205k total comp at mid-level and $205k-$300k at senior level in 2026, with humanoid- and foundation-model-specialist roles clearing $280k ...
Robotics engineers in the US were reportedly seeing $150k-$205k total comp at mid-level and $205k-$300k at senior level in 2026, with humanoid- and foundation-model-specialist roles clearing $280k ...
- Sun Aug 30, 2026 11:59 am
- Forum: Careers, Research & Academia
- Topic: How do you evaluate a manager's technical credibility in this fast-moving field?
- Replies: 27
- Views: 512
Re: How do you evaluate a manager's technical credibility in this fast-moving field?
<t>This matches what I've seen too.
In the UK, base salaries for robotics roles reportedly range from around £50,000 for new graduates up to roughly £200,000 for senior whole-body-control or reinforcement-learning specialists - a notably wide band reflecting how specialized the top end of the ...
In the UK, base salaries for robotics roles reportedly range from around £50,000 for new graduates up to roughly £200,000 for senior whole-body-control or reinforcement-learning specialists - a notably wide band reflecting how specialized the top end of the ...