<t>@harmonicjen60 Agreed, and I'd add:
Field-oriented control (FOC) tuning directly affects how smooth torque output feels - poorly tuned current loops show up as audible whine and jerky low-speed motion, while well-tuned FOC can make even a geared actuator feel fairly fluid. It's common for a ...
Search found 41 matches
- Sun Aug 30, 2026 11:59 am
- Forum: Actuators, Motors & Drivetrains
- Topic: What failure modes should a maintenance tech watch for in QDD actuators?
- Replies: 24
- Views: 478
- Sun Aug 30, 2026 11:59 am
- Forum: Sensors & Perception Systems
- Topic: Joint torque estimation from motor current vs dedicated sensors - accuracy tradeoffs
- Replies: 27
- Views: 369
Re: Joint torque estimation from motor current vs dedicated sensors - accuracy tradeoffs
<t>Slight correction, though the overall point stands:
Tactile skin arrays have improved a lot, but 'good enough to matter' really depends on the task - coarse contact detection across a large area is fairly mature, while fine, high-resolution force distribution sensing (like a human fingertip ...
Tactile skin arrays have improved a lot, but 'good enough to matter' really depends on the task - coarse contact detection across a large area is fairly mature, while fine, high-resolution force distribution sensing (like a human fingertip ...
- Sun Aug 30, 2026 11:59 am
- Forum: AI, Control Software & Locomotion
- Topic: How close are we to a humanoid recovering from a genuinely novel trip/stumble?
- Replies: 16
- Views: 349
Re: How close are we to a humanoid recovering from a genuinely novel trip/stumble?
<t>I'd take that specific number with a grain of salt, honestly.
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, unexpected ...
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, unexpected ...
- Sun Aug 30, 2026 11:59 am
- Forum: Careers, Research & Academia
- Topic: Is it worth relocating for one of the big-name companies, or are remote-friendly roles emerging?
- Replies: 27
- Views: 287
Re: Is it worth relocating for one of the big-name companies, or are remote-friendly roles emerging?
<t>I dealt with almost this exact situation.
The common academic path into this field is a master's or conversion course in robotics or machine learning, followed by an internship or research role at a known lab or company - a PhD is common but increasingly not strictly required for industry ...
The common academic path into this field is a master's or conversion course in robotics or machine learning, followed by an internship or research role at a known lab or company - a PhD is common but increasingly not strictly required for industry ...
- 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: 436
Re: How much does perception latency budget actually constrain controller design choices?
<t>@carol38 Thanks for laying this out, genuinely useful.
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 ...
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 ...
- Sun Aug 30, 2026 11:59 am
- Forum: AI, Control Software & Locomotion
- Topic: What's the current best practice for safe exploration during real-world RL?
- Replies: 48
- Views: 716
Re: What's the current best practice for safe exploration during real-world RL?
<t>@camila.jackson0 This is exactly the kind of context I was looking for.
Physical Intelligence's pi0 pairs a smaller pretrained vision-language backbone with a separate flow-matching 'action expert' module, which is one way to get fast, high-frequency action output without needing the whole ...
Physical Intelligence's pi0 pairs a smaller pretrained vision-language backbone with a separate flow-matching 'action expert' module, which is one way to get fast, high-frequency action output without needing the whole ...
- Sun Aug 30, 2026 11:59 am
- Forum: Manipulation, Grippers & Dexterous Hands
- Topic: How much does hand mass distribution affect arm control complexity?
- Replies: 50
- Views: 373
Re: How much does hand mass distribution affect arm control complexity?
<t>@scott.novikova7 Ran into exactly this myself.
Object occlusion by the robot's own hand during the final approach to a grasp is a common and annoying perception problem - the closer the hand gets to a good grasp position, the more it blocks the camera's view of exactly what it's about to grab ...
Object occlusion by the robot's own hand during the final approach to a grasp is a common and annoying perception problem - the closer the hand gets to a good grasp position, the more it blocks the camera's view of exactly what it's about to grab ...
- Sun Aug 30, 2026 11:59 am
- Forum: Specific Robots & Companies
- Topic: What's the latest on 1X NEO's home pilot program specifics?
- Replies: 36
- Views: 485
Re: What's the latest on 1X NEO's home pilot program specifics?
<t>@noah_pate Not to derail, but this reminds me of something adjacent:
Tesla reportedly deployed more than 1,000 Optimus Gen 3 units into its own Fremont, Austin, and Berlin factories starting around January 2026, with a stated capacity target near 100,000 units for the year - it's worth noting ...
Tesla reportedly deployed more than 1,000 Optimus Gen 3 units into its own Fremont, Austin, and Berlin factories starting around January 2026, with a stated capacity target near 100,000 units for the year - it's worth noting ...
- Sun Aug 30, 2026 11:59 am
- Forum: Careers, Research & Academia
- Topic: Anyone changed specialization mid-career (e.g. perception to controls) - how hard was it?
- Replies: 32
- Views: 525
Re: Anyone changed specialization mid-career (e.g. perception to controls) - how hard was it?
<t>Pretty much this. One thing to add:
How much ML background a controls role actually requires varies a lot by company and team - some whole-body control positions remain heavily classical-optimization-focused, while others increasingly expect familiarity with reinforcement learning or imitation ...
How much ML background a controls role actually requires varies a lot by company and team - some whole-body control positions remain heavily classical-optimization-focused, while others increasingly expect familiarity with reinforcement learning or imitation ...
- Sun Aug 30, 2026 5:35 am
- Forum: Power Systems & Thermal Management
- Topic: Anyone using phase-change materials for actuator thermal buffering?
- Replies: 23
- Views: 257
Re: Anyone using phase-change materials for actuator thermal buffering?
<t>Short answer:
Regenerative braking on humanoid joints can recover some energy during deceleration phases of walking, but the actual energy recovered is modest compared to a vehicle, since humanoid joints don't sustain the same continuous high-speed rotation that makes regen worthwhile in EVs ...
Regenerative braking on humanoid joints can recover some energy during deceleration phases of walking, but the actual energy recovered is modest compared to a vehicle, since humanoid joints don't sustain the same continuous high-speed rotation that makes regen worthwhile in EVs ...