[KongchangAI]
ModelAMP1框架

AMP1

A reference execution framework based on agentic manipulation policies. It is driven by a general-purpose AI model and requires neither low-level skills nor task-specific training, and it can run across single-arm, dual-arm and mobile platforms.

Timeline (last 90 days)

Nov 9

The researchers built the AMP1 reference execution framework, and the same framework runs without modification on three robot embodiments—single-arm, dual-arm and mobile manipulation—with no hardware-specific adaptation for each and no task-related fine-tuning.

Unverified50%
Nov 9

The AMP1 base framework provides no low-level skills for grasping, pushing or placing; all manipulation policies are developed by the agent itself.

Unverified50%
Nov 9

On the RoboLab-120 benchmark, AMP1 achieves an 85.6% success rate zero-shot, while leading VLA and WAM policies reach only 49.2% and 42.9% respectively, and AMP1 uses no demonstration data or task-specific training.

Unverified50%
Nov 9

In real-world tests covering twelve tasks and three robot instances, the AMP1 agent succeeded zero-shot in 104 of 108 trials.

Unverified50%
Nov 9

Compared with strong VLA and WAM baselines, AMP1 reduced the failure rate in real-world tests by 20x and 15x respectively.

Unverified50%
Nov 9

After adding persistent memory storage to the base framework, the agent can carry memory representations across episodes; on the RoboDojo dual-arm manipulation tasks, the memory-equipped version reduced the failure rate by 4.6x compared with zero-shot deployment.

Unverified50%
Nov 9

The researchers observed that the AMP1 agent learned to find hidden objects, use objects as tools, and calibrate the camera on its own—behaviors that were not pre-programmed but emerged as policies of the general model during interaction.

Unverified50%
Nov 9

The AMPs route faces issues such as inference latency, safety and interpretability that require redesign, and AMP1 as a reference framework demonstrates feasibility but is still some distance from productization.

Unverified50%

All Facts (8)

Unverified

The researchers built the AMP1 reference execution framework, and the same framework runs without modification on three robot embodiments—single-arm, dual-arm and mobile manipulation—with no hardware-specific adaptation for each and no task-related fine-tuning.

50%
Unverified

The AMP1 base framework provides no low-level skills for grasping, pushing or placing; all manipulation policies are developed by the agent itself.

50%
Unverified

On the RoboLab-120 benchmark, AMP1 achieves an 85.6% success rate zero-shot, while leading VLA and WAM policies reach only 49.2% and 42.9% respectively, and AMP1 uses no demonstration data or task-specific training.

50%
Unverified

In real-world tests covering twelve tasks and three robot instances, the AMP1 agent succeeded zero-shot in 104 of 108 trials.

50%
Unverified

Compared with strong VLA and WAM baselines, AMP1 reduced the failure rate in real-world tests by 20x and 15x respectively.

50%
Unverified

After adding persistent memory storage to the base framework, the agent can carry memory representations across episodes; on the RoboDojo dual-arm manipulation tasks, the memory-equipped version reduced the failure rate by 4.6x compared with zero-shot deployment.

50%
Unverified

The researchers observed that the AMP1 agent learned to find hidden objects, use objects as tools, and calibrate the camera on its own—behaviors that were not pre-programmed but emerged as policies of the general model during interaction.

50%
Unverified

The AMPs route faces issues such as inference latency, safety and interpretability that require redesign, and AMP1 as a reference framework demonstrates feasibility but is still some distance from productization.

50%

Source Articles