Learning to move autonomously in a hostile world

Figure 1: This sequence was recorded from a live, interactive demo, in which the user controls the crate and can move it anywhere at anytime. A virtual agent is tasked with traveling from the left of the scene to the target on the right. While the agent is running towards the target, the user moves the crate into the position shown on the left, blocking the agent’s intended path. The local motion planner selects frames that avoid hitting the object but still make progress toward the goal (A). The user again moves the object into the agent’s path, and again the system successfully copes (B). Altogether, the user tries to block the agent by moving the crate 3 times, but the agent still dodges it and arrives at the target position seamlessly.