The concept of a developmental program does not mean just to make machines grow from small to big and from simple to complex. It must enable the machine to learn new tasks that a human programmer does not know about at the time of programming. This implies that the representation of any task that the robot learns must be generated by the robot itself, a well known holy grail in AI and fundamental for machine understanding.

In contrast with traditional thoughts that artificial intelligence should be studied within a narrow scope and that otherwise the complexity is out of control, the developmental approach aims to provide a broad and unified developmental framework, which is applicable to a wide variety of perceptual capabilities (e.g., vision, audition and touch), cognitive capabilities (e.g., situation awareness, language understanding, reasoning, planning, communication, decision making, task execution), behavioral capabilities (e.g., speaking, dancing, walking, playing music), motivational capabilities (e.g., pain avoidance, pleasure seeking, what is right and what is wrong) and the fusion of these capabilities. By the very nature of autonomous development, a developmental program does not require humans to manually model task-specific representation. Some recent evidence in neuroscience has suggested that the developmental mechanisms in our brain are probably very similar across different sensing modalities. This is good news since it means that the task of designing a developmental program is probably more tractable than traditional task-specific programming.

Eight requirements for practical AMD
A developmental robot that is capable of practical autonomous mental development (AMD) must deal with the following eight requirements:

1. Environmental openness: Due to the task-nonspecificity, AMD must deal with unknown and uncontrolled environments, including various human environments.
2. High-dimensional sensors: The dimension of a sensor is the number of scalar values per unit time. AMD must directly deal with continuous raw signals from high-dimensional sensors (e.g., vision, audition and taction).
3. Completeness in using sensory information. Due to the environmental openness and task nonspecificity, it is not desirable for a developmental program to discard, at the program design stage, sensory information that may be useful for some future, unknown tasks. Of course, its task-specific representation autonomously derived after birth does discard information that is not useful for a particular task.
4. Online processing: At each time instant, what the machine will sense next depends on what the machine does now.
5. Real-time speed: The sensory/memory refreshing rate must be high enough so that each physical event (e.g., motion and speech) can be temporally sampled and processed in real time (e.g., about 15Hz for vision). This speed must be maintained even when a full (very large but finite) physical "machine brain size'' is used. It must handle one-instance learning: learning from one instance of experience.
6. Incremental processing: Acquired skills must be used to assist in the acquisition of new skills, as a form of ``scaffolding.'' This requires incremental processing. Thus, batch processing is not practical for AMD. Each new observation must be used to update the current complex representation and the raw sensory data must be discarded after it is used for updating.
7. Perform while learning: Conventional machines perform after they are built. An AMD machine must perform while it ``builds'' itself "mentally.''
8. Scale up to large memory: For large perceptual and cognitive tasks, an AMD machine must handle multimodal contexts, large long-term memory and generalization, and capabilities for increasing maturity, all in real time speed.