Quadruped Robots | Research Lab

Autonomous Self-Driving Lab for Robot-Assisted Scientific Experimentation

Mon, 01 Jun 2026 00:00:00 +0000

Project Mission

This project develops autonomous self-driving laboratory systems that integrate robotics, AI, sensing, and scientific instrumentation for end-to-end experimental execution.
We focus on building robotic workflows that can handle samples, transport materials across laboratory spaces, operate analytical instruments, monitor experimental conditions, and generate feedback for the next experimental cycle.

The long-term goal is to move beyond isolated laboratory automation toward a physically embodied discovery platform, where robotic agents can connect experimental planning, sample handling, measurement, analysis, and decision-making in a unified closed-loop system.

Scientific Motivation

Modern scientific experiments often depend on repetitive manual operations, fragile sample handling, instrument-specific procedures, and delayed analysis. These constraints limit throughput, reduce reproducibility, and make it difficult to run experiments continuously across long time horizons.

Self-driving laboratories provide a new framework for scientific discovery by combining AI-driven planning with robotic execution and automated characterization. In this project, we extend that idea from benchtop automation to a broader robotic laboratory architecture that includes dexterous manipulation, mobile sample logistics, real-time monitoring, and future integration with surgical and in vivo experimental systems.

Research Approach

Dexterous Manipulation and Touch Sensing

Touch-Aware Grasping: Developing robotic manipulation policies that use tactile feedback to handle fragile samples, containers, tools, and experimental materials.
Vision-Tactile Fusion: Combining camera-based perception with contact sensing to improve grasp stability, object recognition, and manipulation under uncertain laboratory conditions.
Low-Light Robotic Operation: Designing touch-centered control strategies for dark-lab or lights-out environments where visual sensing alone is insufficient.
Slip and Force Monitoring: Using tactile signals to detect unstable grasps, excessive force, surface contact changes, and potential sample damage.
Skill Learning for Lab Manipulation: Training robots to perform reusable laboratory skills such as picking, placing, uncapping, loading, aligning, and transferring samples.

Robotic Sample Transportation

Quadruped Sample Delivery: Exploring legged robots for transporting samples across laboratories, hallways, stairs, and uneven indoor environments.
Secure Payload Handling: Designing sample carriers that preserve orientation, reduce vibration, and maintain traceability during robotic transport.
Multi-Floor Laboratory Navigation: Planning robot routes that account for stairs, doors, elevators, restricted areas, and handoff points between workstations.
Chain-of-Custody Tracking: Connecting barcodes, RFID, or vision-based sample identification with automated experiment logs.
Human-Robot Lab Coordination: Developing safe interaction protocols for robots operating around researchers, instruments, and sensitive materials.

Automated Experiment Execution and Analysis

Instrument Integration: Connecting robotic arms, liquid handlers, incubators, microscopes, spectrometers, and environmental sensors into a coordinated experimental workflow.
Automated Sample Preparation: Standardizing preparation steps such as dispensing, mixing, incubation, transfer, and measurement setup.
Real-Time Experimental Monitoring: Tracking instrument status, sample condition, environmental variables, and abnormal events during autonomous operation.
AI-Based Data Interpretation: Applying machine learning to analyze imaging, spectroscopy, sensor streams, assay outputs, and experimental metadata.
Closed-Loop Optimization: Using experimental results to update hypotheses, refine protocols, and select the next set of experimental conditions.

System Design

The proposed system is structured as an embodied self-driving lab pipeline. An AI planning module selects experimental objectives and schedules tasks, robotic manipulators execute local operations, a quadruped robot transports samples between physical stations, and analytical instruments produce measurements that are automatically processed by data models.

The laboratory operating layer coordinates these components by managing task queues, robot availability, sample identity, instrument readiness, safety constraints, and data provenance. This architecture allows the platform to operate as a connected experimental ecosystem rather than a collection of independent automation devices.

Current Implementation

At the current stage, this project is structured around modular robotic capabilities rather than a fully autonomous dark lab. The initial focus is on developing robot manipulation policies, tactile sensing modules, sample transportation strategies, and software interfaces for experimental monitoring.

The near-term implementation will evaluate how dexterous manipulators and quadruped robots can coordinate with automated instruments for sample preparation, transport, analysis, and data logging. This stage is designed to establish robust physical execution before expanding toward more complex closed-loop scientific workflows.

Future Research Directions

Future work will extend the platform toward supervised robotic experimentation in biological and biomedical settings. One direction is to integrate surgical robotic systems with automated sample handling, imaging, physiological monitoring, and post-experiment analysis.

The long-term vision is to connect in vitro experiments, animal studies, and in vivo experimental workflows through a unified robotic pipeline. In this framework, surgical robots would support controlled intervention or sample acquisition, mobile robots would manage sample transfer, analytical systems would process measurements, and AI models would monitor outcomes under strict ethical, safety, and regulatory constraints.

This direction is not intended to replace scientific oversight. Instead, the goal is to develop a supervised autonomous experimentation system that improves precision, reproducibility, traceability, and continuity across the full experimental cycle.

Vision-Language-Action Models for Quadruped and Humanoid Robots

Sat, 30 May 2026 00:00:00 +0000

Project Mission

This project develops Vision-Language-Action models for quadruped and humanoid robots. We focus on building embodied AI systems that can understand visual scenes, interpret natural-language instructions, reason about physical environments, and generate robot-specific actions for legged mobility, whole-body movement, and long-horizon planning.

The goal is to move beyond isolated perception, navigation, or control modules toward a unified robot intelligence framework. In this method, quadruped robots and humanoid robots use vision-language reasoning to understand what is happening in the environment, decide what actions are physically possible, and execute specific tasks.

Scientific Motivation

Recent advances in vision-language models (VLMs) have shown strong capabilities in recognizing objects, describing scenes, and reasoning over images and text. However, robots require more than visual reasoning. They must connect perception and language to physical action. A robot must know not only what an object is, but also whether it can approach it, grasp it, avoid it, open it, move it or use it as part of a larger task.

Quadruped and humanoid robots make this problem especially important. A quadruped robot may be able to traverse stairs, uneven terrain, narrow passages, and large indoor or outdoor spaces, but it has limited manipulation capability. A humanoid robot may be able to open doors, operate tools, pick up objects, and interact with human-designed environments, but it requires more complex whole-body balance, motion planning, and manipulation control. The same language instruction may therefore require different interpretations depending on the robot body.

For example, the instruction “check the object on the upper shelf” may require a quadruped robot to navigate to the area, inspect the shelf from multiple viewpoints, and report the object state. For a humanoid robot, the same instruction may involve walking to the shelf, adjusting body posture, reaching with an arm, grasping the object, and possibly relocating it. A general VLA system must understand both the shared task meaning and the embodiment-specific action requirements.

Research Approach

VLA Robot Intelligence

Language-Guided Visual Understanding: Developing models that ground natural-language instructions in robot camera observations, object locations, spatial relations, and task-relevant visual cues.
Embodied Action Reasoning: Connecting visual-language understanding to physically executable robot behaviors such as walking, turning, inspecting, reaching, grasping, and interacting.
Long-Horizon Task Decomposition: Translating high-level human instructions into structured action sequences that can be executed over time by quadruped or humanoid robots.
Affordance-Aware Perception: Estimating what can be walked through, avoided, climbed, reached, grasped, opened, moved, or manipulated from visual observations.
Failure-Aware VLA Control: Detecting when a task cannot be completed from the current observation and triggering replanning, additional perception, or alternative robot actions.

Quadruped Robot Intelligence

Language-Guided Locomotion: Enabling quadruped robots to follow natural-language commands for navigation, inspection, search, and spatial exploration.
Terrain-Aware Navigation: Combining visual perception, proprioception, and environmental cues to move across stairs, slopes, cluttered spaces, narrow paths, and uneven terrain.
Active Visual Inspection: Allowing quadruped robots to move their body and camera viewpoint to inspect objects, rooms, structures, obstacles, or uncertain regions.
Semantic Exploration: Mapping and exploring environments not only by geometry, but also by object categories, room functions, landmarks, and task-relevant regions.
Human-Centered Mobility: Developing navigation behaviors that allow quadruped robots to move safely around people, furniture, doors, corridors, and dynamic obstacles.

Humanoid Robot Intelligence

Whole-Body VLA Control: Developing VLA models that connect language and visual perception to coordinated head, torso, arm, hand, and leg movements.
Bimanual Manipulation: Training humanoid robots to use both hands for object handling, tool use, carrying, opening, pushing, pulling, and coordinated manipulation.
Human-Scale Environment Interaction: Enabling humanoids to interact with doors, handles, shelves, switches, cabinets, tables, chairs, tools, and other objects designed for human bodies.
Posture and Balance-Aware Action: Generating actions that account for center of mass, reachability, foot placement, support surfaces, and whole-body stability.
Socially Situated Robot Action: Studying how humanoid robots should move, gesture, approach, hand over objects, and interact with people in shared spaces.

SLAM and Spatial Understanding

Semantic SLAM for VLA Robots: Using SLAM as one component of the VLA robot system to support localization, spatial memory, object mapping, and long-horizon task execution.
Language-Conditioned Map Querying: Connecting language expressions such as “the room near the stairs,” “the object behind the table,” or “the door on the left” to map-based spatial representations.
Multi-View Scene Understanding: Combining observations from different robot viewpoints to improve object localization, scene reconstruction, and environmental awareness.
Map-Based Task Planning: Using spatial maps to support navigation, inspection, object search, path planning, and task sequencing for both quadruped and humanoid robots.
Dynamic Map Updates: Updating spatial and semantic maps when objects move, doors open, paths become blocked, or robot actions change the environment.

Current Implementation

At the current stage, this project focuses on defining the VLA framework for quadruped and humanoid robot intelligence. The initial implementation is organized around robot vision, natural-language instruction grounding, semantic mapping, and embodiment-specific action generation.

For quadruped robots, the near-term focus is on language-guided navigation, active visual inspection, scene exploration, terrain-aware movement, and semantic SLAM integration. These capabilities provide a foundation for robots that can move through complex environments while interpreting instructions in relation to physical space.

For humanoid robots, the near-term focus is on vision-language-guided reaching, object interaction, whole-body task execution, and manipulation-oriented scene understanding. These capabilities provide a foundation for robots that can operate in human-designed environments and perform tasks requiring arms, hands, posture control, and physical interaction.

Future Research Directions

Future work will extend this project toward general-purpose VLA robot systems that can operate across different embodiments, environments, and task domains. One direction is to develop shared robot foundation models that can interpret language and vision across quadruped and humanoid platforms while producing actions through embodiment-specific control heads.

A further direction is to build simulation-to-real training pipelines for VLA robot policies. Simulation can provide diverse environments, rare failure cases, and scalable task variations, while real-robot experiments can test whether the learned policies remain robust under physical constraints, sensor noise, contact uncertainty, and dynamic environments.