# Vision-based Goal-Reaching Control for Mobile Robots Using a Hierarchical Learning Framework

arXiv: https://arxiv.org/abs/2601.00610 · HTML: https://mlsanity.com/paper/2601.00610/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in RL for robot navigation and UAV control, one of 15 directions in Deep reinforcement learning methods.
- Builds on 15 of its 24 references that are in the map.
- First posted on arXiv 2 Jan 2026.

## Placed in

- Deep reinforcement learning methods / [RL for robot navigation and UAV control](https://mlsanity.com/deeprl/rl-for-robot-navigation-and-uav-control/)

## Builds on (most cited first, 15 of 15)

- [ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM](https://mlsanity.com/paper/2007.11898/) (2020)
- [Lyapunov-based Safe Policy Optimization for Continuous Control](https://mlsanity.com/paper/1901.10031/) (2019)
- [The TUM VI Benchmark for Evaluating Visual-Inertial Odometry](https://mlsanity.com/paper/1804.06120/) (2018)
- [Safe Reinforcement Learning Using Robust Control Barrier Functions](https://mlsanity.com/paper/2110.05415/) (2021)
- [Actor-Critic Reinforcement Learning for Control with Stability Guarantee](https://mlsanity.com/paper/2004.14288/) (2020)
- [Safe reinforcement learning for probabilistic reachability and safety specifications: A Lyapunov-based approach](https://mlsanity.com/paper/2002.10126/) (2020)
- [DynaVINS: A Visual-Inertial SLAM for Dynamic Environments](https://mlsanity.com/paper/2208.11500/) (2022)
- [Integrating DeepRL with Robust Low-Level Control in Robotic Manipulators for Non-Repetitive Reaching Tasks](https://mlsanity.com/paper/2402.02551/) (2024)
- [AIVIO: Closed-loop, Object-relative Navigation of UAVs with AI-aided Visual Inertial Odometry](https://mlsanity.com/paper/2410.05996/) (2024)
- [A Multiplicative Value Function for Safe and Efficient Reinforcement Learning](https://mlsanity.com/paper/2303.04118/) (2023)
- [Robust Sensor-Limited Control with Safe Input-Output Constraints for Hydraulic In-Wheel Motor Drive Mobility Systems](https://mlsanity.com/paper/2409.11823/) (2024)
- [Synthesis of Deep Neural Networks with Safe Robust Adaptive Control for Reliable Operation of Wheeled Mobile Robots](https://mlsanity.com/paper/2508.10634/) (2025)
- [A novel agent with formal goal-reaching guarantees: an experimental study with a mobile robot](https://mlsanity.com/paper/2409.14867/) (2024)
- [Model Reference-Based Control with Guaranteed Predefined Performance for Uncertain Strict-Feedback Systems](https://mlsanity.com/paper/2502.03263/) (2025)
- [Fault-Tolerant Control for System Availability and Continuous Operation in Heavy-Duty Wheeled Mobile Robots](https://mlsanity.com/paper/2502.03278/) (2025)

## Built on by (most cited first, 1 of 1)

- [Reversible Simplex Supervision with Post-Action Debt Accounting for Goal-Reaching RL](https://mlsanity.com/paper/2601.19499/) (2026)

## Abstract (arXiv)

Reinforcement learning (RL) has strong potential in robotics, but exploration-based training complicates safe deployment on large-scale robots. For such applications, this paper proposes a novel hierarchical goal-reaching framework that integrates stereo visual pose estimation, constrained RL-based motion planning, actuator-level robust adaptive control (RAC), and supervisory safe-return logic. Stereo visual localization is used as the real-time pose-estimation interface with loop closing, map fusion, and relocalization. The RL planner generates smooth, feasible goal-reaching references using a problem-specific reward structure and motion constraints that promote goal progress, reduce oscillations, preserve vision-consistent smoothness, and respect the mechanical limits of a heavy skid-steered robot. At the actuation layer, a scaled conjugate-gradient (SCG)-trained deep neural network (DNN) approximates a quasi-static actuator feedforward map from wheel-speed data to nominal control input. This feedforward map is combined with a logarithmic-barrier-based RAC to compensate for residual modeling errors, slip-induced disturbances, and bounded mismatch between the nominal map and real actuator response. For the actuator-level wheel-tracking subsystem, uniformly ultimately bounded tracking with exponential convergence to a disturbance-dependent residual set is established under bounded uncertainty. A logarithmic safety supervisor monitors execution, detects unsafe operating conditions, including faults and localization inconsistencies, and switches the robot to safe-return mode. Experiments on a 6000 kg robot over asphalt and loose-soil terrain demonstrate approximately 3--4 cm final-position root mean square error (RMSE), accurate tracking of RL-generated commands, improved actuator-level performance over two RAC baselines, and successful autonomous recovery after fault injection.