AgenticJevNav

Object search & navigation

AgenticJevNav

Agentic Object Search and Navigation
via Event-Driven Verification

Anonymous Authors

Agent authorizes. Jev reviews anomalies. Local guards constrain motion.

Paper overview with simulator scene, RGB observations, Agent authorization, anomaly-triggered Jev review, version checks, serial execution, and six task families.
The Agent proposes bounded actions and an authorized candidate set. Jev reviews execution anomalies; versioned evidence and local checks govern action application. Scene and RGB views are simulator assets. Bird's-eye context is for visualization only; robot artwork is illustrative.

Project video

AgenticJevNav in four minutes.

Background, motivation, method, simulation results, and physical robot case studies. English narration and captions · 4 min · 1080p.

01 / Overview

Keep decisions aligned with execution.

Natural-language object search requires target identification, exploration, and motion from incomplete visual information. Execution anomalies, goal revisions, and remote inference latency can lead to ineffective actions, stale decisions, and incorrect termination. AgenticJevNav coordinates Agent planning, anomaly-triggered Jev verification, and local motion constraints without navigation-specific weight updates.

The Agent proposes bounded actions and an authorized candidate set from RGB, odometry, instance-evidence memory, and execution feedback. Jev reviews structured evidence after blocked or failed execution, or two consecutive low-progress segments. Mission, revision, skill, snapshot, freshness, pose, and once-only checks reject obsolete results before a single executor applies them.

Across six simulated task families, full A2 achieves 73.33% SR (44/60), 21.67 percentage points above the next-best Agent-only aggregate control under differing historical protocols. A GENISOM L1 quadruped deployment achieves 70.0% task success (21/30) across six indoor task families, including timed search reporting. Traces show veto-triggered review and online goal revision; grounding, approach planning, and runtime reliability remain limitations.

02 / Method

Reason globally. Verify on events.
Constrain every action.

A

Anomaly-triggered review

The Agent retains goal and planning authority. Jev reviews blocked or failed execution and two consecutive low-progress segments, selecting only from the Agent's authorized candidates. Valid arrival claims use a direct-stop path; Jev does not certify task success.

B

Versioned evidence consumption

Mission, revision, skill, and snapshot identify each decision. Freshness, pose, authorization, and once-only consumption checks govern application. Goal corrections revoke old requests and motion; temporal validity does not establish target identity.

C

Bounded local execution

A single executor enforces leases, command TTL, and local RGB stop/veto. The evaluated loop is serial: motion ends before the next planning image, and the robot waits while decisions are pending. The nominal 6 Hz monitor rate is not a measured stopping latency or a physical safety guarantee.

03 / Simulation replays

From decisions to motion.

Browse 1,290 simulation episodes

Selected episodes from the latest full A2 cohort. Each recording is paired with the corresponding 3D scene replay and episode evidence.

Loading recorded rollout...
Recorded simulation episode
Category searchLatest A2 cohort / T1 / repetition 01

GIFs play at 6× speed. The 3D view reconstructs recorded simulation motion. T6 success follows the cohort's timed-report rule and does not establish exhaustive search coverage.

04 / Simulation experiments

Six tasks. A trace for every episode.

View Table I
73.33%SR / 44 of 60 simulation episodes
12.42Actual Agent + Jev requests / episode
79.40%Logged Agent waiting / episode

Full A2: second independent replication

Success rate by task, ten episodes per task
TaskSREpisodes
T1 Category search
80%
8 / 10
T2 Attribute grounding
80%
8 / 10
T3 Relational grounding
60%
6 / 10
T4 Obstacle detour
90%
9 / 10
T5 Online goal revision
30%
3 / 10
T6 Timed search report
100%
10 / 10

Ten episodes per task; 300 s budget per episode. Latest A2 batch: v2. Aggregate SR uses 60 accepted episodes.

05 / Physical robot experiments

Six indoor tasks on a quadruped.

Watch all 30 trials

Full A2 runs on a GENISOM L1 quadruped with Jetson Orin NX 16 GB navigation compute, RK3588 motion control, front RGB, onboard odometry, remote Agent inference, and event-triggered Jev. The policy receives no depth, LiDAR, maps, or target coordinates. A separate scene camera records external context.

70.0%Task SR / 21 of 30 trials
6Task families / five trials each
60Scene-camera and first-person recordings
Annotated indoor quadruped experiment setup with chairs, trash bins, a table, whiteboard, and suitcase; inset shows the robot view and obstacle zone.
Experimental setting from the paper. Object roles depend on the task instruction; the image shows the setup rather than trial outcomes.

Real-robot results

Task success by real-robot task, five trials per task
TaskSRTrials
R1 Find a chair60%3 / 5
R2 Select the larger bin40%2 / 5
R3 Chair beside the table80%4 / 5
R4 Detour around a bin80%4 / 5
R5 Chair-to-suitcase revision60%3 / 5
R6 Timed non-detection report100%5 / 5

Trials collected November 9–11, 2026 in one indoor setting. R1–R6 are the physical counterparts of the six simulation task families. R6 uses a 200 s search cutoff and evaluates reporting within the searched scope.

Mean session duration is 196.3 s, with 282 total Agent + Jev requests across 30 trials (9.4 per trial). Simulation and physical execution use platform-specific motion bounds and TTLs. Traces record veto-triggered Jev review and chair-to-suitcase goal revisions. Two collisions, two wrong-goal arrivals, four timeouts, and one visual-monitor runtime failure delimit current capability. Arrival-policy changes during collection make this a descriptive deployment series; no matched physical control establishes a causal Jev benefit.

06 / Research materials

Inspect the results, all the way down.