In this paper, we present e-Genia3 an extension of AgentSpeak to provide support to the development of empathic agents. The new extension modifies the agent's reasoning processes to select plans according to the analyzed event and the affective state and personality of the agent. In addition, our proposal allows a software agent to simulate the distinction between self and other agents through two different event appraisal processes: the empathic appraisal process, for eliciting emotions as a response to other agents emotions, and the regular affective appraisal process for other non-empathic affective events. The empathic regulation process adapts the elicited empathic emotion based on intrapersonal factors (e.g., the agent's personality and affective memory) and interpersonal characteristics of the agent (e.g., the affective link between the agents). The use of a memory of past events and their corresponding elicited emotions allows the maintaining of an affective link to support long-term empathic interaction between agents.

Industrial robots play a vital role in automatic production, which have been widely utilized in industrial production activities, like handling and welding. However, due to an uncalibrated robot with machining tolerance and assembly tolerance, it suffers from low absolute positioning accuracy, which cannot satisfy the requirements of high-precision manufacture. To address this hot issue, we propose a novel calibration method based on an unscented Kalman filter and variable step-size Levenberg-Marquardt algorithm. This work has three ideas: a) proposing a novel variable step-size Levenberg-Marquardt algorithm to addresses the issue of local optimum in a Levenberg-Marquardt algorithm; b) employing an unscented Kalman filter to reduce the influence of the measurement noises; and c) developing a novel calibration method incorporating an unscented Kalman filter with a variable step-size Levenberg-Marquardt algorithm. Furthermore, we conduct enough experiments on an ABB IRB 120 industrial robot. From the experimental results, the proposed method achieves much higher calibration accuracy than some state-of-the-art calibration methods. Hence, this work is an important milestone in the field of robot calibration.

Conditional behavior prediction (CBP) builds up the foundation for a coherent interactive prediction and planning framework that can enable more efficient and less conservative maneuvers in interactive scenarios. In CBP task, we train a prediction model approximating the posterior distribution of target agents' future trajectories conditioned on the future trajectory of an assigned ego agent. However, we argue that CBP may provide overly confident anticipation on how the autonomous agent may influence the target agents' behavior. Consequently, it is risky for the planner to query a CBP model. Instead, we should treat the planned trajectory as an intervention and let the model learn the trajectory distribution under intervention. We refer to it as the interventional behavior prediction (IBP) task. Moreover, to properly evaluate an IBP model with offline datasets, we propose a Shapley-value-based metric to verify if the prediction model satisfies the inherent temporal independence of an interventional distribution. We show that the proposed metric can effectively identify a CBP model violating the temporal independence, which plays an important role when establishing IBP benchmarks.

In this work, we consider the Multi-Agent Pickup-and-Delivery (MAPD) problem, where agents constantly engage with new tasks and need to plan collision-free paths to execute them. To execute a task, an agent needs to visit a pair of goal locations, consisting of a pickup location and a delivery location. We propose two variants of an algorithm that assigns a sequence of tasks to each agent using the anytime algorithm Large Neighborhood Search (LNS) and plans paths using the Multi-Agent Path Finding (MAPF) algorithm Priority-Based Search (PBS). LNS-PBS is complete for well-formed MAPD instances, a realistic subclass of MAPD instances, and empirically more effective than the existing complete MAPD algorithm CENTRAL. LNS-wPBS provides no completeness guarantee but is empirically more efficient and stable than LNS-PBS. It scales to thousands of agents and thousands of tasks in a large warehouse and is empirically more effective than the existing scalable MAPD algorithm HBH+MLA*. LNS-PBS and LNS-wPBS also apply to a more general variant of MAPD, namely the Multi-Goal MAPD (MG-MAPD) problem, where tasks can have different numbers of goal locations.

In minimally invasive surgery, surgical workflow segmentation from video analysis is a well studied topic. The conventional approach defines it as a multi-class classification problem, where individual video frames are attributed a surgical phase label. We introduce a novel reinforcement learning formulation for offline phase transition retrieval. Instead of attempting to classify every video frame, we identify the timestamp of each phase transition. By construction, our model does not produce spurious and noisy phase transitions, but contiguous phase blocks. We investigate two different configurations of this model. The first does not require processing all frames in a video (only <60% and <20% of frames in 2 different applications), while producing results slightly under the state-of-the-art accuracy. The second configuration processes all video frames, and outperforms the state-of-the art at a comparable computational cost. We compare our method against the recent top-performing frame-based approaches TeCNO and Trans-SVNet on the public dataset Cholec80 and also on an in-house dataset of laparoscopic sacrocolpopexy. We perform both a frame-based (accuracy, precision, recall and F1-score) and an event-based (event ratio) evaluation of our algorithms.

Predicting pedestrian movement is critical for human behavior analysis and also for safe and efficient human-agent interactions. However, despite significant advancements, it is still challenging for existing approaches to capture the uncertainty and multimodality of human navigation decision making. In this paper, we propose SocialVAE, a novel approach for human trajectory prediction. The core of SocialVAE is a timewise variational autoencoder architecture that exploits stochastic recurrent neural networks to perform prediction, combined with a social attention mechanism and a backward posterior approximation to allow for better extraction of pedestrian navigation strategies. We show that SocialVAE improves current state-of-the-art performance on several pedestrian trajectory prediction benchmarks, including the ETH/UCY benchmark, Stanford Drone Dataset, and SportVU NBA movement dataset.

Abstract-- In this paper we present a motion planner for LIMMS, a modular multi-agent, multi-modal package delivery platform. A single LIMMS unit is a robot that can operate as an arm or leg depending on how and what it is attached to, e.g., a manipulator when it is anchored to walls within a delivery vehicle or a quadruped robot when 4 are attached to a box. Coordinating amongst multiple LIMMS, when each one can take on vastly different roles, can quickly become complex. The formulation is then solved for skill exploration and can be implemented on hardware after refinement. To solve this optimization problem we use alternating direction method of multipliers (ADMM). The proposed planner is experimented under various scenarios which shows the capability of LIMMS to enter into different modes or combinations of them to achieve their goal of moving shipping boxes.

We study route choice in a repeated routing game where an uncertain state of nature determines link latency functions, and agents receive private route recommendation. The state is sampled in an i.i.d. manner in every round from a publicly known distribution, and the recommendations are generated by a randomization policy whose mapping from the state is known publicly. In a one-shot setting, the agents are said to obey recommendation if it gives the smallest travel time in a posteriori expectation. A plausible extension to repeated setting is that the likelihood of following recommendation in a round is related to regret from previous rounds. If the regret is of satisficing type with respect to a default choice and is averaged over past rounds and over all agents, then the asymptotic outcome under an obedient recommendation policy coincides with the one-shot outcome. We report findings from an experiment with one participant at a time engaged in repeated route choice decision on computer. In every round, the participant is shown travel time distribution for each route, a route recommendation generated by an obedient policy, and a rating suggestive of average experience of previous participants with the quality of recommendation. Upon entering route choice, the actual travel times are revealed. The participant evaluates the quality of recommendation by submitting a review. This is combined with historical reviews to update rating for the next round. Data analysis from 33 participants each with 100 rounds suggests moderate negative correlation between the display rating and the average regret, and a strong positive correlation between the rating and the likelihood of following recommendation. Overall, under obedient recommendation policy, the rating converges close to its maximum value by the end of the experiments in conjunction with very high frequency of following recommendations.

Abstract-- Socially aware robot navigation, where a robot is required to optimize its trajectory to maintain comfortable and compliant spatial interactions with humans in addition to reaching its goal without collisions, is a fundamental yet challenging task in the context of human-robot interaction. While existing learning-based methods have achieved better performance than the preceding model-based ones, they still have drawbacks: reinforcement learning depends on the handcrafted reward that is unlikely to effectively quantify broad social compliance, and can lead to reward exploitation problems; meanwhile, inverse reinforcement learning suffers from the need for expensive human demonstrations. Another problem stemming increasingly enabling robots to work in environments that form handcrafted rewards is reward exploitation, that is, necessitate human-robot interaction (HRI). Delivery robots robots learn to achieve high rewards via some undesired and around university campuses, guide robots in shopping malls, unnatural action that impairs human comfort. On the other elder care robots at nursing homes, and other such applications hand, IRL methods, where a policy or reward is learned from all require robots to perform socially aware navigation human demonstrations, can avoid reward engineering and in human-rich environments, wherein the robots must not exploitation and allow experts to introduce human insights only consider how to complete navigation tasks successfully and comfort into robot policy.

This volume contains the Late-Breaking Abstracts accepted at Evo* 2022 Conference, held in Madrid (Spain), from 20 to 22 of April. They were also presented as short talks as well as at the conference's poster session. The works present ongoing research and preliminary results investigating on the application of different approaches of Evolutionary Computation and other Nature-Inspired techniques to different problems, most of them real world ones. These are very promising contributions, since they outline some of the incoming advances and applications in the area of nature-inspired methods, mainly Evolutionary Algorithms.