In October 2021, we introduced that we acquired the MuJoCo physics simulator, and made it freely out there for everybody to help analysis in all places. We additionally dedicated to growing and sustaining MuJoCo as a free, open-source, community-driven challenge with best-in-class capabilities. In the present day, we’re thrilled to report that open sourcing is full and the whole codebase is on GitHub!
Right here, we clarify why MuJoCo is a superb platform for open-source collaboration and share a preview of our roadmap going ahead.
A platform for collaboration
Physics simulators are crucial instruments in trendy robotics analysis and infrequently fall into these two classes:
- Closed-source, industrial software program.
- Open-source software program, typically created in academia.
The primary class is opaque to the person, and though generally free to make use of, can’t be modified and is tough to know. The second class typically has a smaller person base and suffers when its builders and maintainers graduate.
MuJoCo is among the few full-featured simulators backed by a longtime firm, which is actually open supply. As a research-driven organisation, we view MuJoCo as a platform for collaboration, the place roboticists and engineers can be part of us to develop one of many world’s finest robotic simulators.
Options that make MuJoCo notably enticing for collaboration are:
- Full-featured simulator that may model complex mechanisms.
- Readable, performant, transportable code.
- Simply extensible codebase.
- Detailed documentation: each user-facing and code feedback.
We hope that colleagues throughout academia and the OSS group profit from this platform and contribute to the codebase, enhancing analysis for everybody.
As a C library with no dynamic reminiscence allocation, MuJoCo may be very quick. Sadly, uncooked physics velocity has traditionally been hindered by Python wrappers, which made batched, multi-threaded operations non-performant as a result of presence of the World Interpreter Lock (GIL) and non-compiled code. In our roadmap beneath, we tackle this concern going ahead.
For now, we’d prefer to share some benchmarking outcomes for 2 frequent fashions. The outcomes had been obtained on a normal AMD Ryzen 9 5950X machine, operating Home windows 10.
Right here’s our near-term roadmap for MuJoCo:
- Unlock MuJoCo’s velocity potential with batched, multi-threaded simulation.
- Help bigger scenes with enhancements to inside reminiscence administration.
- New incremental compiler with higher mannequin composability.
- Help for higher rendering by way of Unity integration.
- Native help for physics derivatives, each analytical and finite-differenced.
Be taught extra
Useful sources about MuJoCo:
We sit up for receiving your contributions!