Often, when modeling human decision-making behaviors in th e context of human-robot teaming, the emotion aspect of human is ignored. Nevertheless, the influence of em otion, in some cases, is not only undeniable but beneficial. This work studies the humanlike characteristics brought b y regret emotion in one-human-multi-robot teaming for the application of domain search. In such application, the task management load is outsourced to the robots to reduce the human's workload, freeing the human to do more important work. The regret decision model is first used by each robot for deciding whether to request human service, th en is extended for optimally queuing the requests from multiple robots. For the movement of the robots in the domain search, we designed a path planning algorithm based on dynamic programming for each robot. The simulation shows that the humanlike characteristics, namely, risk-seeking and risk-aversion, indeed bring some appealing eff ects for balancing the workload and performance in the human-multi-robot team.

Recent successes of Reinforcement Learning (RL) allow an agent to learn policies that surpass human experts but suffers from being time-hungry and data-hungry. By contrast, human learning is significantly faster because prior and general knowledge and multiple information resources are utilized. In this paper, we propose a Planner-Actor-Critic architecture for huMAN-centered planning and learning (PACMAN), where an agent uses its prior, high-level, deterministic symbolic knowledge to plan for goal-directed actions, and also integrates the Actor-Critic algorithm of RL to fine-tune its behavior towards both environmental rewards and human feedback. This work is the first unified framework where knowledge-based planning, RL, and human teaching jointly contribute to the policy learning of an agent. Our experiments demonstrate that PACMAN leads to a significant jump-start at the early stage of learning, converges rapidly and with small variance, and is robust to inconsistent, infrequent, and misleading feedback.

Mutual exclusion (mutex) can be traced back to concurrency control, which refers to the condition that prevents simultaneous accesses to a shared resource. In knowledge representation, they specify the constraints that some properties cannot hold at the same time. For example, an object cannot be at different locations at the same time. These constraints frequently occur in applications from model-checking problems in computer-aided verification [2], computer vision [12, 17], graph algorithms [11], and AI planning [14]. The goal of this paper is to develop a graph-theoretic technique for compactly encoding large sets of mutex constraints and apply it to planning in ASP . We do his by focusing on domain-independent AI planning as started out by SA TPlan [10]. That is, we will first obtain an ASP planner by a straightforward translation from SA TPlan and then study how to encode mutex constraints compactly for the planner. In SA T/ASP planning, mutex constraints are specified by formulas/rules that, for any state (which involves a time step, also called a layer in this paper), the actions with conflicting preconditions or effects, and the fluents that are inferred to be conflicting, are mutually exclusive. A naive encoding of these constraints can certainly generate enough rules to overwhelm the underlying solver for large planning instances.

This literature review focuses on three important aspects of an autonomous car system: tracking (assessing the identity of the actors such as cars, pedestrians or obstacles in a sequence of observations), prediction (predicting the future motion of surrounding vehicles in order to navigate through various traffic scenarios) and decision making (analyzing the available actions of the ego car and their consequences to the entire driving context). For tracking and prediction, approaches based on (deep) neural networks and other, especially stochastic techniques, are reported. For decision making, deep reinforcement learning algorithms are presented, together with methods used to explore different alternative actions, such as Monte Carlo Tree Search.

Real-time multi-target path planning is a key issue in the field of autonomous driving. Although multiple paths can be generated in real-time with polynomial curves, the generated paths are not flexible enough to deal with complex road scenes such as S-shaped road and unstructured scenes such as parking lots. Search and sampling-based methods, such as A* and RRT and their derived methods, are flexible in generating paths for these complex road environments. However, the existing algorithms require significant time to plan to multiple targets, which greatly limits their application in autonomous driving. In this paper, a real-time path planning method for multi-targets is proposed. We train a fully convolutional neural network (FCN) to predict a path region for the target at first. By taking the predicted path region as soft constraints, the A* algorithm is then applied to search the exact path to the target. Experiments show that FCN can make multiple predictions in a very short time (50 times in 40ms), and the predicted path region effectively restrict the searching space for the following A* search. Therefore, the A* can search much faster so that the multi-target path planning can be achieved in real-time (3 targets in less than 100ms).

Many intelligent systems currently interact with others using at least one of fixed communication inputs or preset responses, resulting in rigid interaction experiences and extensive efforts developing a variety of scenarios for the system. Fixed inputs limit the natural behavior of the user in order to effectively communicate, and preset responses prevent the system from adapting to the current situation unless it was specifically implemented. Closed-loop interaction instead focuses on dynamic responses that account for what the user is currently doing based on interpretations of their perceived activity. Agents employing closed-loop interaction can also monitor their interactions to ensure that the user responds as expected. We introduce a closed-loop interactive agent framework that integrates planning and recognition to predict what the user is trying to accomplish and autonomously decide on actions to take in response to these predictions. Based on a recent demonstration of such an assistive interactive agent in a turn-based simulated game, we also discuss new research challenges that are not present in the areas of artificial intelligence planning or recognition alone.

Space exploration missions have seen use of increasingly sophisticated robotic systems with ever more autonomy. Deep learning promises to take this even a step further, and has applications for high - level tasks, like path planning, as well as low - level tasks, like motion control, which are critical components for mission efficiency and success. Using deep reinforcement end - to - end learning with randomized reward function parameters during training, we teach a simulated 8 degree - of - freedom quadruped ant - like robot to travel anywhere within a perimeter, conducting path plan and motion control on a single neural network, without any system model or prior knowledge of the terrain or environment. Our approach also allows for user specified waypoints, which could translate well to either fully autonomous or semi - autonomous/tele - operated space applications that encounter delay times. We train ed the agent using randomly ge nerated waypoints linked to the reward function and passed waypoint coordinates as inputs to the neural network. Such applications show promise on a variety of space exploration robots, including high speed rovers for fast locomotion and legged cave robots for rough terrain.

During 15-17 September, RaySearch will exhibit its latest advances in oncology software at the American Society for Radiation Oncology (ASTRO) 2019 annual meeting in Chicago, USA. On show will be new development in machine learning technology and automation in the RayStation* treatment planning system and the RayCare * oncology information system. Machine learning capabilities were added already in RayStation 8B and are being continuously improved. RaySearch has now been granted FDA 510(k) clearance for deep learning organ segmentation and for machine learning automated planning for a key model. Several planning models are being validated for future FDA 510(k) clearance.

During 15-17 September, RaySearch will exhibit its latest advances in oncology software at the American Society for Radiation Oncology (ASTRO) 2019 annual meeting in Chicago, USA. On show will be new development in machine learning technology and automation in the RayStation* treatment planning system and the RayCare * oncology information system. Machine learning capabilities were added already in RayStation 8B and are being continuously improved. RaySearch has now been granted FDA 510(k) clearance for deep learning organ segmentation and for machine learning automated planning for a key model. Several planning models are being validated for future FDA 510(k) clearance.

Invitae is a healthcare technology company that leverages genetic information to empower doctors and patients to make informed medical decisions. Our software engineers work on a variety of projects ranging from innovations in healthcare systems to taming the chaos of biology. We're constantly improving our tools and technologies to deliver the highest quality actionable information to doctors and patients. Invitae AI is seeking a computer scientist with expertise in AI planning and reinforcement learning to develop state of the art solutions to problems in process automation, recommender systems, and human-in-the-loop user interfaces. The desired candidate is a strong coder with professional software engineering experience as well as a scientist interested in developing and publishing state of the art methods with the Invitae AI team.