Robotics Simulation
Using tools such as NVIDIA Isaac Sim, we recreate robots, task objects, and workspaces in virtual environments to validate and improve robot motion.
Our work covers simulator selection, custom virtual environments, learning and AI model refinement with tools such as Isaac Lab, and transfer to physical hardware.
Using collected and prepared data, we identify differences between simulation and physical robots and connect the results to deployment in the field.
3 Development Areas
Virtual Environment
Use simulation tools such as NVIDIA Isaac Sim to recreate robot geometry and motion ranges, task objects, and surrounding equipment in a virtual environment.
Configure physical conditions and sensors for the motions being tested and build an environment for repeatable trials.
Motion Validation
Run tasks such as grasping, handling, and navigation in simulation to check completion, interference, and execution time.
Vary objects and operating conditions to identify issues and improve robot motion and AI models.
Sim to Real
Design interfaces and test procedures for transferring validated motions and settings to physical robots.
Identify and adjust for differences on hardware, and connect the work to Edge AI deployment where needed.
Work Type
Review the robot, tasks, and available data to define the validation scope and evaluation methods.
Evaluate environments such as NVIDIA Isaac Sim for the required physics, sensor simulation, and hardware interfaces, then select a suitable configuration.
Model the robot, task objects, and workspace and configure the conditions needed for validation.
Incorporate collected and prepared data, including hardware dimensions and motion logs.
Define task sequences and test conditions, then compare completion, contact and interference, and execution time.
Repeat trials under varied conditions to identify motions and task stages that need improvement.
Refine motion settings and control logic based on validation results.
Where AI is used, support simulation-based learning with tools such as Isaac Lab and tune models for the robot and task, comparing behavior before and after changes.
Define hardware checks, operating ranges, interfaces, and test procedures.
Validate and refine the work for the target hardware and site conditions, then hand over simulation results for deployment.
EXDREAM R&D / Robot Decision System
Robot Decision Data
Our Robot Decision System (RDS) creates decision-learning data from robot motion logs, sensor data, operator histories, and simulation results.
We are developing task-specific decision datasets that capture states, candidate actions, selected actions, and outcomes for grasping, handling, and navigation.
Robot Decision Model
We are researching and developing lightweight AI models that evaluate and select the next action or skill using the prepared decision data.
Through training and tuning for company-specific procedures and equipment conditions, we aim to support robot task decisions.
Robot Decision Harness
We are researching and developing mechanisms that adapt decision methods and compute to task complexity, risk, and the current state.
We simulate combinations of models and decision methods under the same conditions, comparing success rates, decision latency, and failure stages to inform hardware validation.
DELIVERABLES
Deliver a virtual environment recreating the robot, task objects, and workspace in an agreed format.
Include execution conditions and operating and configuration guidance for continued testing.
Deliver developed and refined motion settings and test software with the validation conditions and results.
Include AI models, motion logs, and evaluation data according to the agreed development scope.
Organize validated motions, settings, and remaining hardware checks for deployment and field testing.
Where needed, continue through Edge AI development and implementation.
Step
Review the robot and tasks to define the motions to validate, available data, and evaluation criteria.
Select the simulator and recreate the robot, task objects, and workspace.
Run tasks under varied conditions and check completion, interference, and execution time.
Refine motion and AI models, comparing results under the same conditions to guide improvement.
Test and refine on physical hardware, connecting the results to deployment and field validation.
3 OFFERING TYPES
Based on your team structure and your project’s scope, scale, and goals, you can choose from the following three engagement models.
Around once a week
1–3 people
We create development plans for each company’s projects, document requirements, and support development team formation and vendor negotiations.
We also review actual progress and provide support to keep development projects running smoothly.
Around three days a week
1–3 people
We join your development team as your tech lead and work alongside you on design and development.
We share practical expertise and provide educational content, including seminars, so your employees can continue development independently after the project ends.
Embedded on site
Up to 5 people, depending on project scale
EXDREAM’s development team works on site at your company, handling everything from planning and coding to deployment.
For companies without engineers, we serve as your dedicated development team.
For companies with an existing engineering team, we join forces and work together toward successful delivery.
Services, team size, engagement frequency, duration, and responsibilities can be flexibly tailored to each project.
START A PROJECT