Service robots that perform manipulation must solve task-and-motion planning (TAMP) problems, which require joint reasoning about symbolic task structure and continuous geometric feasibility. This paper proposes a Hierarchical Task Network (HTN)-based TAMP framework that integrates PDDLStream-style conditional generators (streams) through an explicit world-model layer. In the proposed formalism, HTN procedures (methods) invoke streams that sample continuous parameters depending on the current geometric state. When a stream fails, it returns diagnostic information that is propagated up the hierarchy, enabling selective backtracking that avoids revisiting irrelevant branches of the search tree. We further introduce a forward-progression search procedure that combines depth-first expansion with failure-guided jumps based on this feedback. We evaluate the proposed approach on kitchen manipulation benchmarks executed by a dual-arm service robot. Profiling shows that 99% of planning time is spent in generator calls, predominantly on trajectory generation, while symbolic reasoning contributes negligible overhead. The results demonstrate that tight symbolic–geometric integration with informed backtracking improves robustness and efficiency in long-horizon manipulation planning. We release the ProgHTN-BackStream planner together with benchmark descriptions and a dataset collected during the study, and report ablation experiments assessing the impact of key algorithmic components.

A robot system is designed as a set of embodied agents. An embodied agent is decomposed into cooperating subsystems. In our previous work activities of subsystems were defined by hierarchical finite state machines. With their states activities were associated. In that approach communication between subsystems was treated as an implementation issue. This paper represents activities of a robot system using hierarchical Petri nets with conditions. Such net is created by specifying consecutive layers: multi-agent robot system layer, agent layer, subsystem layer, behaviour layer and communication layer. This decomposition not only organizes in a systematic manner the development of a robot system, but also introduces a comprehensive description of concurrently acting subsystems. Based on those theoretical considerations, a tool was created for producing hierarchical Petri nets defining the model of a robotic system and enabling automatic generation of the robot controller code, resulting in a significant acceleration of the implementation phase. The capabilities of the tool are presented by the development of a robot controller performing a rudimentary task.

Visual servos are inherently inaccurate due to lower resolution of reasonably priced cameras and poor calibration of robot-camera relative position and robot kinematic model. Instead of trying to improve those factors the paper presents an alternative solution in which the grasping operation is aided by force control which accommodates positional inaccuracies. The developed control law utilizes the superposition of visually generated desired position and desired mechanical impedance of the manipulator.

With our proposed decomposition into layers, a generic framework leading to the reuse of previously produced software and the extraction of useful portions can be achieved. The presented transition function based formalism can be applied to specifying programming frameworks for robot controllers executing very diverse tasks. Formalization introduces rigor into the discussion of the structure of embodied agent controllers. The paper deals with systems consisting of multiple agents executing jobs by: influencing the environment through effectors, gathering information from the environment through sensors and communicating with the other agents through communication channels. A paradigm shift is proposed: from building systems executing jobs, to agents acquiring resources (effectors and receptors) so that they can execute the jobs assigned to them. A supervisory controller coordinates the adequate sequencing of jobs and resolves contentions.