Base Layer Robotics

Changelog & Updates

Chronological progress of the Base Layer Robotics effort.

Dojo V2: Agentic Infrastructure & MCP

Implemented Model Context Protocol (MCP) server support, enabling direct agentic interaction with Dojo's training and evaluation pipelines. Hardened CLI payloads, added experiment hooks, and unified logging policies to support large-scale automated research sweeps.

Dojo V2: Sensor-First Migration

Migrating Dojo towards a single standard where every world exposes raw sensor sources. Entities now own their sensors, brains, and memory, deprecating legacy omniscient observe APIs in favor of embedded-ready SensorSuite pipelines.

B1 Balance Bot Integration

Upgraded physics capabilities and implemented a command-conditioned balance controller. The underlying kinematic integrations and pseudo-huber temporal budgets are now fully stabilized for hardware transfer.

Vectorized Cluster Buffer (VCB) V1

Shipped the initial GPU-resident VCB for train-hp, allowing multi-actor clustered ingest with persistent step-stamped snapshots to optimize steady-state learning.