refactor: remove navigation tasks (#638)

Author: jmatejcz

docs/simulation_and_benchmarking/rai_bench.md

@@ -130,7 +130,6 @@ The ToolCallingAgentBenchmark class manages the execution of tasks and collects
 There are predefined Tasks available which are grouped by categories:
 
 -   Basic - require retrieving info from certain topics
--   Navigation
 -   Spatial reasoning - questions about surroundings with images attached
 -   Manipulation
 -   Custom Interfaces - requires using messages with custom interfaces

src/rai_bench/rai_bench/docs/tool_calling_agent_benchmark.md

@@ -14,4 +14,4 @@ Implementations can be found:
 
 -   Validators [Validators](../tool_calling_agent/validators.py)
 -   Subtasks [Validators](../tool_calling_agent/tasks/subtasks.py)
--   Tasks, including navigation, spatial, custom interfaces and other [Tasks](../tool_calling_agent/tasks/)
+-   Tasks, including basic, spatial, custom interfaces and manipulation [Tasks](../tool_calling_agent/tasks/)

src/rai_bench/rai_bench/examples/benchmarking_models.py

@@ -36,7 +36,6 @@
         task_types=[  # what types of tasks to include
             "basic",
             "spatial_reasoning",
-            # "navigation",
             "custom_interfaces",
             "manipulation",
         ],

src/rai_bench/rai_bench/test_models.py

@@ -96,14 +96,12 @@ class ToolCallingAgentBenchmarkConfig(BenchmarkConfig):
         Literal[
             "basic",
             "manipulation",
-            "navigation",
             "custom_interfaces",
             "spatial_reasoning",
         ]
     ] = [
         "basic",
         "manipulation",
-        "navigation",
         "custom_interfaces",
         "spatial_reasoning",
     ]