Skip to main content
Stretch Lab

Planning

Stretch 5

Lessons, the landscape, technology trends, the AI roadmap and architecture for the next generation.

Stretch's competitive moat is its AI ecosystem, not hardware. With 216+ GitHub stars on stretch_ai, the largest mobile manipulation research community, and integration into Open X-Embodiment, Hello Robot is the default platform for home robot AI research. Stretch 5 should double down by upgrading compute () and making the AI developer experience frictionless: the best-integrated AI platform for home manipulation research.

Strategic priorities

  1. compute upgradeEnables models, future-proofs AI stack
  2. + dedicated busesEliminates critical firmware reliability risk ( reentrancy)
  3. ESP32-S3 with defined UART protocolClean WiFi/BLE/OTA architecture
  4. eFuse power protectionSafety + FCC compliance
  5. FCC Class B design-inRequired for consumer market
  6. Enhanced Dex Teleop + pipelineData flywheel is the long-term moat

Competitive landscape

Competing platforms
PlatformCompanyPriceStatusThreatDifferentiator
Stretch 3Hello Robot$24,950ShippinglowLightest, most affordable research platform
TIAGoPAL Robotics~$80K+ShippinglowFull humanoid torso, industrial-grade, ROS
Mobile Stanford (open-source)~$30K BOMResearchhighBimanual, learning from demonstration focus
Unitree G1/H1Unitree$16K–$90KShippinghighHumanoid, legged locomotion, Chinese supply chain
Figure 02Figure AIN/APilot programsmediumGeneral-purpose humanoid, massive VC backing
1X NEO1X TechnologiesN/APre-productionmediumHome humanoid, backed by OpenAI
HuggingFace (open-source)OpenActivehighStandardized framework, could commoditize Stretch's role

Single neural networks that take images + language instructions and output robot actions directly. (Physical Intelligence) and (Google DeepMind) represent the leading edge.

Diffusion Policy

For Stretch 5: Stretch 5 compute must support 3B+ parameter models at >5 Hz inference. Requires dedicated GPU ().

AI/ML integration roadmap

Near-Term (6–12 months)

  1. Object GraspingNow: OWL-v2 detection → heuristic graspWith foundation models: model (-style) generates grasp trajectories end-to-end
  2. Task PlanningNow: LLM prompt → fixed operation sequenceWith foundation models: LLM with affordance grounding — plans only feasible actions
  3. NavigationNow: A* / RRT on voxel mapWith foundation models: Learned navigation policies for dynamic obstacles + social norms
  4. Voice InteractionNow: Whisper STT → GPT-4o → Piper TTSWith foundation models: On-device multimodal model (Gemma/Qwen) for low-latency, private interaction

Medium-Term (12–24 months)

  1. Dexterous Manipulation via Now: Manual programmingWith foundation models: Dex Teleop + Diffusion Policy — learn to fold laundry, load dishwashers, sort items
  2. Autonomous ExplorationNow: Pre-mapped navigationWith foundation models: DynaMem + LLM-guided exploration ('go find all dirty dishes')
  3. PersonalizationNow: Static configurationWith foundation models: Fine-tune to individual homes — learn object locations, user preferences, layouts
  4. Multi-Robot CoordinationNow: Single robot onlyWith foundation models: Two Stretch robots with bimanual Dex Teleop for complex tasks

Long-Term (24+ months)

  1. World ModelsNow: Reactive control onlyWith foundation models: Predictive models of home physics — enables planning without trial-and-error
  2. Embodied QA & MonitoringNow: No passive monitoringWith foundation models: 'Is the stove off?' 'Did grandma take her medicine?' — always-on home awareness via VLMs

Compute requirements for AI stack

Compute requirements
Model classExampleParametersMin VRAMSpeed
Vision encoderSIGLip-so400m400M2 GB30+ FPS
Object detectorOWL-v2 large300M3 GB10+ FPS
SegmentationSAM2-base90M2 GB15+ FPS
LLM (local)Qwen2.5-7B7B6 GB20 tok/s
model-small3B8 GB5+ Hz
Full stackPerception + LLM + 12–16 GBPipelined

Recommendation: NX 16 GB as baseline, Orin AGX 64 GB for flagship. This future-proofs Stretch 5 for the model wave.

  1. V1 PIMU: Added INA228 power monitor, pre-charge circuit, safe PC shutdown, system shutdown mode (103µA vs 12–30mA), brake button float mode, IMU+Mag, better USB hub ICs
  2. Charging improved: 10A (2.5hrs vs 4.5hrs)Requires 36V 8A adapter specifically
  3. BMS comms limited to 9600bpsBlocking at 1kHz was problematic
  4. EMC: USB hub renumeration from ESD fixed with new ICsGrounding still critical
  5. Stretch 3 passed Class A EMC in both operational and charging modes

Development roadmap

  1. 1Architecture & Schematic
    • Define power architecture (Efuse, INA228 alerts)
    • Consolidate 3V3 rails
    • Master/slave UART protocol spec
    • Select Class B EMC-friendly USB hub ICs
    • Select NX vs AGX for compute
    • Design with dedicated buses (IMU/Mag/INA228 separated)
  2. 2Prototype & Bring-up
    • In-house pre-compliance EMC scans
    • Actuator protection validation
    • Non-blocking implementation + transfers
    • Reverse current path testing
    • integration + AI stack validation
    • ESP32-S3 UART protocol bring-up
  3. 3Validation & Compliance
    • FCC Class B formal testing
    • Automated RDK test suite complete
    • SOC accuracy validation (INA228 vs BMS)
    • System grounding audit
    • model inference benchmarks on Orin
    • Dex Teleop + pipeline validation
  4. 4Production Readiness
    • Final BOM review & cost optimization
    • Manufacturing test fixtures
    • Firmware OTA update pipeline (via ESP32-S3)
    • Documentation & handoff
    • 'Contribute data' toggle for fleet learning