Traditional multi-robot motion planning (MMP) focuses on computing trajectories for multiple robots acting in an environment, such that the robots do not collide when the trajectories are taken simultaneously. In safety-critical applications, a human supervisor may want to verify that the plan is indeed collision-free. In this work, we propose a notion of explanation for a plan of MMP, based on visualization of the plan as a short sequence of images representing time segments, where in each time segment the trajectories of the agents are disjoint, clearly illustrating the safety of the plan. We show that standard notions of optimality (e.g., makespan) may create conflict with short explanations. Thus, we propose meta-algorithms, namely multi-agent plan segmenting-X (MAPS-X) and its lazy variant, that can be plugged on existing centralized sampling-based tree planners X to produce plans with good explanations using a desirable number of images. We demonstrate the efficacy of this explanation-planning scheme and extensively evaluate the performance of MAPS-X.

We develop a deep generative model built on a fully differentiable simulator for multi-agent trajectory prediction. Agents are modeled with conditional recurrent variational neural networks (CVRNNs), which take as input an ego-centric birdview image representing the current state of the world and output an action, consisting of steering and acceleration, which is used to derive the subsequent agent state using a kinematic bicycle model. The full simulation state is then differentiably rendered for each agent, initiating the next time step. We achieve state-of-the-art results on the INTERACTION dataset, using standard neural architectures and a standard variational training objective, producing realistic multi-modal predictions without any ad-hoc diversity-inducing losses. We conduct ablation studies to examine individual components of the simulator, finding that both the kinematic bicycle model and the continuous feedback from the birdview image are crucial for achieving this level of performance. We name our model ITRA, for "Imagining the Road Ahead".

The domain of Embodied AI has recently witnessed substantial progress, particularly in navigating agents within their environments. These early successes have laid the building blocks for the community to tackle tasks that require agents to actively interact with objects in their environment. Object manipulation is an established research domain within the robotics community and poses several challenges including manipulator motion, grasping and long-horizon planning, particularly when dealing with oft-overlooked practical setups involving visually rich and complex scenes, manipulation using mobile agents (as opposed to tabletop manipulation), and generalization to unseen environments and objects. We propose a framework for object manipulation built upon the physics-enabled, visually rich AI2-THOR framework and present a new challenge to the Embodied AI community known as ArmPointNav. This task extends the popular point navigation task to object manipulation and offers new challenges including 3D obstacle avoidance, manipulating objects in the presence of occlusion, and multi-object manipulation that necessitates long term planning. Popular learning paradigms that are successful on PointNav challenges show promise, but leave a large room for improvement.

Leveraging the latent heat of phase change materials (PCMs) can reduce the peak temperatures and transient variations in temperature in electronic devices. But as the power levels increase, the thermal conduction pathway from the heat source to the heat sink limits the effectiveness of these systems. In this work, we evaluate embedding the PCM within the silicon device layer of an electronic device to minimize the thermal resistance between the source and the PCM to minimize this thermal resistance and enhance the thermal performance of the device. The geometry and material properties of the embedded PCM regions are optimized using a combination of parametric and machine learning algorithms. For a fixed geometry, considering commercially available materials, Solder 174 significantly outperforms other organic and metallic PCMs. Also with a fixed geometry, the optimal melting points to minimize the peak temperature is higher than the optimal melting point to minimize the amplitude of the transient temperature oscillation, and both optima increase with increasing heater power. Extending beyond conventional optimization strategies, genetic algorithms and particle swarm optimization with and without neural network surrogate models are used to enable optimization of many geometric and material properties. For the test case evaluated, the optimized geometries and properties are similar between all ML-assisted algorithms, but the computational time depends on the technique. Ultimately, the optimized design with embedded phase change materials reduces the maximum temperature rise by 19% and the fluctuations by up to 88% compared to devices without PCM.

Existing approaches for generating human-aware agent behaviors have considered different measures of interpretability in isolation. Further, these measures have been studied under differing assumptions, thus precluding the possibility of designing a single framework that captures these measures under the same assumptions. In this paper, we present a unifying Bayesian framework that models a human observer's evolving beliefs about an agent and thereby define the problem of Generalized Human-Aware Planning. We will show that the definitions of interpretability measures like explicability, legibility and predictability from the prior literature fall out as special cases of our general framework. Through this framework, we also bring a previously ignored fact to light that the human-robot interactions are in effect open-world problems, particularly as a result of modeling the human's beliefs over the agent. Since the human may not only hold beliefs unknown to the agent but may also form new hypotheses about the agent when presented with novel or unexpected behaviors.

Spoken dialogue is the most natural way for people to interact with complex autonomous agents such as robots. Future Army operational environments will require technology that allows artificial intelligent agents to understand and carry out commands and interact with them as teammates. Researchers from the U.S. Army Combat Capabilities Development Command, known as DEVCOM, Army Research Laboratory and the University of Southern California's Institute for Creative Technologies, a Department of Defense-sponsored University Affiliated Research Center, created an approach to flexibly interpret and respond to Soldier intent derived from spoken dialogue with autonomous systems. This technology is currently the primary component for dialogue processing for the lab's Joint Understanding and Dialogue Interface, or JUDI, system, a prototype that enables bi-directional conversational interactions between Soldiers and autonomous systems. "We employed a statistical classification technique for enabling conversational AI using state-of-the-art natural language understanding and dialogue management technologies," said Army researcher Dr. Felix Gervits. "The statistical language classifier enables autonomous systems to interpret the intent of a Soldier by recognizing the purpose of the communication and performing actions to realize the underlying intent."

Inefficient traffic control may cause numerous problems such as traffic congestion and energy waste. This paper proposes a novel multi-agent reinforcement learning method, named KS-DDPG (Knowledge Sharing Deep Deterministic Policy Gradient) to achieve optimal control by enhancing the cooperation between traffic signals. By introducing the knowledge-sharing enabled communication protocol, each agent can access to the collective representation of the traffic environment collected by all agents. The proposed method is evaluated through two experiments respectively using synthetic and real-world datasets. The comparison with state-of-the-art reinforcement learning-based and conventional transportation methods demonstrate the proposed KS-DDPG has significant efficiency in controlling large-scale transportation networks and coping with fluctuations in traffic flow. In addition, the introduced communication mechanism has also been proven to speed up the convergence of the model without significantly increasing the computational burden.

We introduce two methods for improving the performance of agents meeting for the first time to accomplish a communicative task. The methods are: (1) `message mutation' during the generation of the communication protocol; and (2) random permutations of the communication channel. These proposals are tested using a simple two-player game involving a `teacher' who generates a communication protocol and sends a message, and a `student' who interprets the message. After training multiple agents via self-play we analyse the performance of these agents when they are matched with a stranger, i.e. their zero-shot communication performance. We find that both message mutation and channel permutation positively influence performance, and we discuss their effects.

As more machine learning agents interact with humans, it is increasingly a prospect that an agent trained to perform a task optimally, using only a measure of task performance as feedback, can violate societal norms for acceptable behavior or cause harm. Value alignment is a property of intelligent agents wherein they solely pursue non-harmful behaviors or human-beneficial goals. We introduce an approach to value-aligned reinforcement learning, in which we train an agent with two reward signals: a standard task performance reward, plus a normative behavior reward. The normative behavior reward is derived from a value-aligned prior model previously shown to classify text as normative or non-normative. We show how variations on a policy shaping technique can balance these two sources of reward and produce policies that are both effective and perceived as being more normative. We test our value-alignment technique on three interactive text-based worlds; each world is designed specifically to challenge agents with a task as well as provide opportunities to deviate from the task to engage in normative and/or altruistic behavior.

Object-centric representations have recently enabled significant progress in tackling relational reasoning tasks. By building a strong object-centric inductive bias into neural architectures, recent efforts have improved generalization and data efficiency of machine learning algorithms for these problems. One problem class involving relational reasoning that still remains under-explored is multi-agent reinforcement learning (MARL). Here we investigate whether object-centric representations are also beneficial in the fully cooperative MARL setting. Specifically, we study two ways of incorporating an agent-centric inductive bias into our RL algorithm: 1. Introducing an agent-centric attention module with explicit connections across agents 2. Adding an agent-centric unsupervised predictive objective (i.e. not using action labels), to be used as an auxiliary loss for MARL, or as the basis of a pre-training step. We evaluate these approaches on the Google Research Football environment as well as DeepMind Lab 2D. Empirically, agent-centric representation learning leads to the emergence of more complex cooperation strategies between agents as well as enhanced sample efficiency and generalization.