Applied Intuition

Can we achieve state-of-the-art for mainstream E2E and vectorized driving benchmarks without using any human demonstration data? Terra series at @AppliedInt now tops the NAVSIM, HUGSim, nuPlan val14 and InterPlan benchmarks, powered by self-play RL without imitation, scaling in closed loop with all agents being reactive. 🚘 With TerraZero released a few months ago, we set the SOTA on vectorized benchmarks like nuPlan val14 and InterPlan, powered by our super high-throughput self-play RL framework experiencing 25 centuries of challenging driving scenarios. 📽️ In June this year, TerraTransfer was released as the first of its kind to bring the SOTA vectorized policy from self play (TerraZero) to an E2E policy via image-to-vector encoder alignment, which topped the HUGSim closed-loop score. 🔚 This week, we are thrilled to release TerraTransfer++, a demonstration-free E2E planner setting the SOTA for NAVSIM and HUGSim, by adding planning capability from self-play rollout experience to TerraTransfer. Setting SOTA for public benchmarks is just a beginning, as we have seen the journey from pioneering work like UniAD to successful mass production of E2E ADAS in the industry, but what makes me quite excited is to see the strong signal from a new paradigm with potential to refactorize how the next generation autonomy can be developed, and bring the scalability, safety and performance to the next level. We are the believer of data and scaling, but not just human demonstration data and open-loop scaling like imitation or open-loop RL (AV2.0) - we have the bet on closed-loop scaling with both synthetic and real-world data (AV3.0), and the Terra series is the starting point of the journey towards real product with our bet. Great work from the team @caffe_tt, Weixin Li, Zhouchonghao Wu, @AkshayRangesh, Saarth Bonde, Grantland Hall, @ChenTangMark, Yihan Hu, for creating TerraTransfer and TerraTransfer++! TerraTransfer++ report:  arxiv.org/abs/2610.30319 TerraTransfer++ website: terra-applied.github.io/Terr… TerraTransfer report: arxiv.org/abs/2606.17386

Reinforcement Learning (RL) in simulation is a scalable strategy to learn dexterous skills, but naive exploration from scratch often fails to discover manipulation strategies for diverse objects. At @AppliedInt, we propose X-Reset, a straightforward method to resolve the exploration problem for generalist RL policies by randomly sampling resets from human hand-object states. - We train a single dexterous policy to manipulate a variety of objects to any goal pose, ranging from small markers to heavy powerdrills with zero teleoperation data - The learned policy zero-shot generalizes well beyond the training set (DexYCB), and transfers from sim-to-real using object pose-tracking models We are continuously expanding robotics research at @AppliedInt beyond X-Reset, with the bounds of simulation and synthetic data for dexterous manipulation pushed. Stay tuned and join us! 🌐 Project Page: xreset-applied.github.io 📄 Paper: arxiv.org/abs/2609.35715