Prediction-for-CompAction: navigation in social environments using generalized cognitive maps

TL;DR

Prediction-for-CompAction addresses how robots can navigate human environments by modeling cooperative and noncooperative interactions as recursive cognition via compact cognitive maps. The authors introduce PfCA and a neural architecture comprising a trajectory modeling neural network (TMNN) and a causal neural network (CNN) to project dynamic scenes into static maps that serve planning. They demonstrate that cooperation (CoUs) reduces effective obstacles and enables shorter, safer trajectories without increasing average social effort in many scenarios, though cooperation can be detrimental in certain crowd configurations and a robot should switch strategies. The work provides a framework for learning and memory within artificial agents, enabling adaptive social navigation in crowds and offering guidance for real-world humanoid-robot interaction.

Abstract

The ultimate navigation efficiency of mobile robots in human environments will depend on how we will appraise them: merely as impersonal machines or as human-like agents. In the latter case, an agent may take advantage of the cooperative collision avoidance, given that it possesses recursive cognition, i.e.,the agent's decisions depend on the decisions made by humans that in turn depend on the agent's decisions. To deal with this high-level cognitive skill, we propose a neural network architecture implementing Prediction-for-CompAction paradigm. The network predicts possible human-agent collisions and compacts the time dimension by projecting a given dynamic situation into a static map. Thereby emerging compact cognitive map can be readily used as a "dynamic GPS" for planning actions or mental evaluation of the convenience of cooperation in a given context. We provide numerical evidence that cooperation yields additional room for more efficient navigation in cluttered pedestrian flows, and the agent can choose path to the target significantly shorter than a robot treated by humans as a functional machine. Moreover, the navigation safety, i.e., the chances to avoid accidental collisions, increases under cooperation. Remarkably, these benefits yield no additional load to the mean society effort. Thus, the proposed strategy is socially compliant, and the humanoid agent can behave as "one of us".

Figures (7)

• Figure 1: Cognition through compact cognitive maps in a static environment. A) A humanoid agent (green circle) walks avoiding collisions with a static human (black circle) and a chair (black square). B) The situation is mapped from the real space (left) to the network space (right) described by a 2D neural lattice. C) A wavefront propagating in the lattice simulates multiple agent's trajectories (three snapshots at mental time $\tau=\tau_{1,2,3}$). The front explores the environment and creates a gradient profile. D) Final cognitive map with effective obstacles (in black). Going up the gradient the agent can reach the target avoiding obstacles (blue arrowed lines). E) Example of navigation. The agent follows one of the possible trajectories (superimposed frames with increasing green intensity correspond to progressively increasing time instants).
• Figure 2: Cognition through compact cognitive maps in a dynamic situation. A) Same as in Fig. \ref{['fig_CIR_Static']}A, but now the human walks towards the chair. B) Simulation of the agent's movements (wavefront) and matching them with obstacles' movements (human's trajectory, dashed line, is predicted by the TMNN). Collisions of the wavefront and virtual obstacles produce effective obstacles. C) Compact cognitive map (the time dimension has been compacted) with static effective obstacle (black). Going up the gradient (blue arrowed curves) ensures collision-free walking. D) Agent navigating in the real space.
• Figure 3: Noncooperative navigation (AvUs paradigm). A) An agent expects no cooperation from a human. At the risk of a collision the agent steps away (light green arrow), while the human goes straightforward (black arrow). B) Compact cognitive map. The effective obstacle (black area) forces the agent to steer its trajectory (blue arrowed curve).
• Figure 4: Cooperative navigation (CoUs paradigm). A) Same as Fig. \ref{['Fig4a']}A, but now the human cooperates in collision avoidance (light grey arrow). B) Cooperation occurs only if the CoUs agent enters the human's reaction zone under a proper angle. C) The agent can go either to the right, $\rm R_{CoUs}$, or to the left, $\rm L_{CoUs}$, expecting the human response $\rm R_{hum}$ and $\rm L_{hum}$, respectively. The intersection of two personal zones forms a virtual obstacle to be avoided (area delimited by black solid curve). D) The process of mental exploration of possible movements (note decreasing size of the virtual obstacle). E) Cooperation reduces the effective obstacle in the compact cognitive map (compare to Fig. \ref{['Fig4a']}B) and enables more efficient navigation. F) Example of navigation (superimposed frames with increasing color intensity correspond to progressively increasing time instants).
• Figure 5: Performance gain provided by cooperation in a cluttered crowd (CoUs vs AvUs paradigm): A) Initial situation. An agent (green circle) goes along a corridor to a door against pedestrian flow (black circles). Arrows indicate the pedestrians' velocities. B) Compact cognitive maps created under non-cooperative (left) and cooperative (right) behaviors. Black areas correspond to effective obstacles. Arrowed curves show possible paths to the door. C) Examples of navigation of the AvUs (left) and CoUs (right) agents (superimposed frames with increasing color intensity correspond to progressively increasing time instants). D) Measures of the navigation performance (mean and std). Stars mark statistically significant difference, $p < 0.05$.