Robot Episodic Memory

Robots remember places, objects and outcomes.

Industry	Level	Difficulty	Recommended mode
Robotics & automotive	4 of 5	Expert	sq8

Coming soon

A complete, runnable Robot Episodic Memory reference implementation is in progress. The architecture and core code below already work with SrvDB 0.3.

The problem

• Robots forget past experience.
• Cloud memory adds latency.
• Power loss wipes state.

How SrvDB powers Robot Episodic Memory

1. Observations are embedded and stored on the robot.
2. Recall by current context.
3. Crash-safe persist().
4. Rust API in the robot stack.

What changes

Today	With Robot Episodic Memory on SrvDB
Stateless robots	Experience memory
Cloud latency	In-process recall
State lost on power cut	Crash-safe

How it works

1. Embed observations.
2. Store locally.
3. Recall in planning.
4. Persist at safe points.
5. Compact periodically.

SrvDB features it uses

• Rust API: embed SrvDB directly in Rust services and devices.
• Crash-safe persist(): after it returns, data survives a crash or power loss and reopens exactly as committed.
• SQ8 compression (sq8): stores each value in one byte, 4× smaller than full precision.
• delete and compact(): remove items immediately from search, then reclaim disk space.

Use cases

• Place recognition
• Object memory
• Task outcomes
• Human preferences
• Navigation hints
• Failure avoidance

Core code

embed() is your embedding model (for example sentence-transformers, or a function that turns your records into feature vectors).

import json
import srvdb

db = srvdb.Database("./robot-episodic-memory-db", dimension=256, mode="sq8")

def ingest(items):
    """items: list of (id, text, metadata dict)"""
    db.upsert(
        ids=[i for i, _, _ in items],
        embeddings=[embed(t) for _, t, _ in items],
        metadatas=[json.dumps(m) for _, _, m in items],
    )
    db.persist()                      # crash-safe checkpoint

def recall(observation, k=5):
    hits = db.search(embed(observation), k)
    return [(json.loads(db.get(i)), round(score, 3)) for i, score in hits]

Limits and honest notes

• Validate memory use in safety-relevant behaviour.

Build roadmap

1. Prototype: load a sample of real data with flat mode and check that searches return what an expert expects.
2. Measure: if you move to an approximate mode, compare its results with flat on the same queries (recall).
3. Pipeline: add continuous upsert and decide when to call persist().
4. Harden: test restarts and crashes, add logging, review every output path with domain experts.
5. Deploy: ship the database directory with the application or service.

All Robotics & automotive projects

Level	Project	What it does
1 · Beginner	In-car Manual Assistant	Answers drivers’ questions from the owner’s manual, offline.
2 · Intermediate	Diagnostic Assistant	Technicians match symptoms and trouble codes to past repairs.
3 · Advanced	Scenario Miner	Finds driving or robot episodes similar to a scenario of interest.
4 · Expert	Robot Episodic Memory (this page)	Robots remember places, objects and outcomes.
5 · Frontier	Autonomous Fleet Memory	Share learned experience across a fleet with database snapshots.

See also: Use cases · Live examples (coming soon)